Neuronpedia: open-source interpretability platform hosting Anthropic's Jacobian Lens and Gemma Scope 2
techNmak · x · 2026-09-04
Entries 13-14 of @techNmak's visual learning resource thread:
- Diffusion Explainer: interactively walks through the major components behind Stable Diffusion, so "denoise from noise" stops being a black box.
- Neuronpedia: an open-source interpretability platform for inspecting model internals — explore features, sparse-autoencoder latents, activations, and attribution-style graphs, backed by 5TB+ of activations and explanations. Recent highlights include Anthropic's Jacobian Lens (revealing a global workspace in LLMs), Natural Language Autoencoders (translating a model's internal thoughts into text), Assistant Axis, Circuit Tracer, and Google DeepMind's Gemma Scope 2 (SAEs and transcoders for Gemma 3), plus a new interp-engine for fast, standardized interpretability.
Related event: Tools for Model Interpretability: Neuronpedia and Diffusion Explainer(2 posts)→
More from Apps
- Startup Electric Plant builds an AI model to decipher plants' electrical signals — TechCrunch AI · 2026-10-21
- Dev builds an open-source minimalist launcher for Xiaomi TVs: big fonts, wallpaper rotation, HDMI shortcuts — op7418 · 2026-10-20
- Lawyer tip: don't just ask AI for answers, have it red-team your work and explain why — jkubicki · 2026-10-20
- Mintlify launches Autopilot beta: an always-on agent that keeps docs in sync with your code — ycombinator · 2026-10-20
- Steam needs real quality control on AI slop, not an AI art ban, argues designer — AIandDesign · 2026-10-20
- Perplexity Computer now runs fully local on Mac, model and agent on-device — perplexity_ai · 2026-10-20