© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166261
    Prev
    Next
    INDEX
    Explanations

    will

    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_31_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
    汇报
    0.42
    utas
    0.39
     deciding
    0.38
     दिग्विजय
    0.38
     RAIL
    0.38
     विजयी
    0.38
    逍
    0.37
     INVALID
    0.36
    эль
    0.36
     निर्णय
    0.35
    POSITIVE LOGITS
    カスタ
    0.36
    जिए
    0.34
     Balancing
    0.33
     gql
    0.33
    Balanced
    0.33
    изо
    0.33
     Balanced
    0.33
    ข้อ
    0.32
     scalability
    0.32
    傃
    0.32
    Activations Density 0.002%

    No Known Activations