© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125221
    Prev
    Next
    INDEX
    Explanations

    male, Old, Ridgway, Boric

    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_3_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
    s
    0.78
    al
    0.71
    る
    0.69
    wk
    0.67
    and
    0.66
    EX
    0.66
    .
    0.66
    oL
    0.64
    eni
    0.63
    SH
    0.63
    POSITIVE LOGITS
    ки
    0.77
    خ
    0.74
    ری
    0.65
    де
    0.62
    я
    0.60
    ;
    0.59
     itineraries
    0.59
    ف
    0.59
    ী
    0.57
    ۰
    0.57
    Activations Density 0.001%

    No Known Activations