© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79700
    Prev
    Next
    INDEX
    Explanations

    manhood, humorous

    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_0_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
    n
    2.28
    a
    2.03
    C
    1.89
    m
    1.83
    ’
    1.55
    س
    1.55
    M
    1.52
    P
    1.48
    in
    1.44
    न
    1.44
    POSITIVE LOGITS
    ۳
    1.48
    ۰
    1.29
    ไม่ใช่
    1.27
     or
    1.23
    {
    1.20
    。
    1.14
     are
    1.13
     لی
    1.13
     tasse
    1.13
    。『
    1.09
    Activations Density 0.000%

    No Known Activations