© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112012
    Prev
    Next
    INDEX
    Explanations

    ROSTOVA, sott

    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_2_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
    м
    1.63
    م
    1.39
    н
    1.38
    רים
    1.25
    ли
    1.22
    .
    1.16
    น
    1.03
    в
    1.02
    ன்
    1.02
    й
    1.02
    POSITIVE LOGITS
     in
    1.65
    ERS
    1.38
     to
    1.05
    CS
    1.04
    dV
    0.98
    kval
    0.98
    ES
    0.97
    CL
    0.97
     প্রায়
    0.95
    ){
    0.93
    Activations Density 0.000%

    No Known Activations