© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138515
    Prev
    Next
    INDEX
    Explanations

    userscript metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_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
    mla
    0.39
    macd
    0.39
    ,/*
    0.38
    /-/
    0.38
    peror
    0.38
     duke
    0.38
     jīn
    0.38
     ஆண்டில்
    0.36
    sbom
    0.36
    王朝
    0.36
    POSITIVE LOGITS
     moulded
    0.39
     Blackstone
    0.38
     Mould
    0.38
    Პ
    0.38
     Blackburn
    0.38
    强度
    0.38
    Mold
    0.37
     Unis
    0.37
     Supplied
    0.37
     Moors
    0.37
    Activations Density 0.000%

    No Known Activations