© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24243
    Prev
    Next
    INDEX
    Explanations

    trainings and bookings regarding

    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_10_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
    ти
    0.57
    ;
    0.54
    ាទ
    0.51
     intuit
    0.50
    答应
    0.50
    ното
    0.49
    idoscope
    0.49
    ات
    0.46
    йки
    0.45
     excepciones
    0.45
    POSITIVE LOGITS
    ifferent
    0.64
     플레이
    0.64
    used
    0.63
    real
    0.61
    ivariate
    0.61
    valmentaja
    0.60
    駋
    0.60
    ze
    0.60
    posed
    0.60
     ولی
    0.60
    Activations Density 0.000%

    No Known Activations