© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206197
    Prev
    Next
    INDEX
    Explanations

    command line arguments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    //*
    0.45
    /...
    0.40
    /
    0.37
    //!
    0.36
    /√
    0.36
    ////////////
    0.34
     //#
    0.34
    \,\
    0.33
     newToken
    0.33
     assertFalse
    0.32
    POSITIVE LOGITS
     /
    0.68
     :
    0.36
    SET
    0.36
     ؛
    0.34
    графія
    0.34
     '
    0.32
     About
    0.32
     Building
    0.32
     ;
    0.31
     Internationale
    0.31
    Activations Density 0.002%

    No Known Activations