© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209368
    Prev
    Next
    INDEX
    Explanations

    sleepy

    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
    2
    0.81
    t
    0.70
    ²)
    0.67
    plyr
    0.63
    日期
    0.61
     mesto
    0.61
    acija
    0.58
     capilla
    0.58
    于
    0.58
     bullpen
    0.57
    POSITIVE LOGITS
    м
    0.84
    م
    0.79
    ur
    0.78
    гре
    0.73
    conoc
    0.71
    ?
    0.71
    !
    0.67
    ходу
    0.65
     tracheal
    0.65
    ع
    0.64
    Activations Density 0.002%

    No Known Activations