© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202979
    Prev
    Next
    INDEX
    Explanations

    keep it secret

    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_12_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
    is
    0.75
    this
    0.63
    ur
    0.61
    as
    0.57
    i
    0.57
    u
    0.56
    movie
    0.54
    biggest
    0.54
     Mã
    0.54
     गोपनीयता
    0.53
    POSITIVE LOGITS
    ك
    0.63
     zapatos
    0.54
    溃
    0.51
    ه
    0.51
     Lint
    0.50
    ంటి
    0.50
     էր
    0.49
    ﾙ
    0.49
    كز
    0.49
     pregunt
    0.49
    Activations Density 0.001%

    No Known Activations