© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107759
    Prev
    Next
    INDEX
    Explanations

    Hawkins and Hawthorne

    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_1_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
    t
    1.54
    y
    1.32
    ing
    1.17
    ال
    1.14
    ת
    1.13
    الط
    1.04
    ก
    1.03
    ط
    1.02
     in
    1.02
    r
    1.02
    POSITIVE LOGITS
    ید
    1.08
    -
    1.07
     ރ
    0.97
    jit
    0.95
    I
    0.92
    owskiego
    0.91
    Verlag
    0.90
    렸
    0.90
    وی
    0.89
    INE
    0.89
    Activations Density 0.000%

    No Known Activations