© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107670
    Prev
    Next
    INDEX
    Explanations

    ขออนุญาต, ขอคำ, ขอหัวหน้า

    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_2_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
    ן
    1.28
    ߋ
    1.07
    حر
    1.00
    ٠
    0.98
    FUNCTION
    0.98
     núcle
    0.96
    0.96
    ak
    0.95
    ang
    0.95
    Gravestone
    0.95
    POSITIVE LOGITS
    ва
    1.78
     with
    1.69
    ב
    1.68
    ة
    1.67
     was
    1.65
     of
    1.57
    ات
    1.46
    ing
    1.38
    ление
    1.38
    я
    1.37
    Activations Density 0.000%

    No Known Activations