© 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. 204373
    Prev
    Next
    INDEX
    Explanations

    rec or rese

    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
    ك
    1.06
    ক
    1.01
    because
    1.00
    ↵↵
    0.95
    ۰
    0.95
    ０
    0.93
    at
    0.93
     obiettivo
    0.88
     Verhalten
    0.88
    wohner
    0.87
    POSITIVE LOGITS
    รวม
    0.84
     are
    0.77
     It
    0.77
    ੇ
    0.77
    綃
    0.77
     of
    0.76
    ীবনী
    0.75
    зация
    0.74
    是
    0.74
     universe
    0.72
    Activations Density 0.000%

    No Known Activations