© 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. 35601
    Prev
    Next
    INDEX
    Explanations

    Herbert and place names

    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
     quoting
    0.61
    로
    0.61
     quoted
    0.58
    面の
    0.58
     jedną
    0.56
    面に
    0.56
     shipped
    0.54
    a
    0.54
     นั้น
    0.53
     nhàng
    0.53
    POSITIVE LOGITS
    ли
    0.91
    ä
    0.77
    وم
    0.70
    ai
    0.69
     The
    0.67
    ب
    0.61
     Rukh
    0.60
    ೋ
    0.59
    ummer
    0.58
     Kareena
    0.58
    Activations Density 0.003%

    No Known Activations