© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2667
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    न
    2.27
    К
    2.25
    𝗮
    2.06
    પણે
    1.96
    स
    1.86
    те
    1.84
    ﺎ
    1.84
    あと
    1.83
    ﻘ
    1.83
     достижения
    1.79
    POSITIVE LOGITS
    و
    2.07
    '^
    1.90
    newcommand
    1.89
    sniffer
    1.78
    ஜ்மஹால்
    1.77
     što
    1.74
    modifier
    1.70
    𝙢
    1.70
     extrav
    1.70
     ocurr
    1.69
    Activations Density 0.012%

    No Known Activations