© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133376
    Prev
    Next
    INDEX
    Explanations

    python app initialization

    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_6_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
    in
    1.19
    t
    1.14
    л
    1.11
    p
    1.09
    و
    1.09
    и
    1.07
    st
    0.98
    ו
    0.97
    d
    0.95
    u
    0.91
    POSITIVE LOGITS
     that
    1.04
    ıları
    0.84
    ك
    0.84
     THAT
    0.78
     inglês
    0.77
     énergie
    0.77
     algún
    0.75
     intérieure
    0.75
     agua
    0.75
     espaço
    0.75
    Activations Density 0.002%

    No Known Activations