© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18614
    Prev
    Next
    INDEX
    Explanations

    fake, normalization, license

    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_15_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
     極
    0.17
     농
    0.15
     `:`,
    0.14
     $(-
    0.14
     innumerable
    0.14
     ж
    0.13
     tiap
    0.13
     Evans
    0.13
     Ida
    0.13
    立場
    0.13
    POSITIVE LOGITS
     Conexion
    0.14
    зи
    0.13
    quee
    0.13
    ຽ
    0.13
     concludes
    0.13
     yena
    0.13
    صميم
    0.13
    ameras
    0.13
    0
    0.13
    超时
    0.13
    Activations Density 0.019%

    No Known Activations