© 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. 198716
    Prev
    Next
    INDEX
    Explanations

    Sir Walter Scott

    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
     घंटों
    0.85
    지
    0.83
    ल
    0.82
     moieties
    0.80
    어
    0.79
    사
    0.77
    श
    0.76
    자
    0.75
     phonons
    0.74
     eddies
    0.72
    POSITIVE LOGITS
    as
    0.83
    y
    0.81
    am
    0.81
    '
    0.79
    ิ
    0.72
    ()->
    0.71
    erie
    0.68
    Drawable
    0.68
    ти
    0.68
    ،
    0.68
    Activations Density 0.000%

    No Known Activations