© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193707
    Prev
    Next
    INDEX
    Explanations

    table driven parser

    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_4_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
    d
    0.96
    a
    0.79
    Р
    0.77
    e
    0.75
    dah
    0.70
     a
    0.69
    c
    0.67
    Have
    0.67
    고
    0.67
     it
    0.66
    POSITIVE LOGITS
    ль
    0.93
    ísima
    0.79
    ти
    0.75
    ות
    0.73
    é
    0.71
     deced
    0.70
     curtailed
    0.69
     angiogenic
    0.69
    is
    0.68
     transgenic
    0.67
    Activations Density 0.000%

    No Known Activations