© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34196
    Prev
    Next
    INDEX
    Explanations

    stack navigation, paper, cultures, nations, life, libraries

    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_3_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
    stieg
    0.65
    utat
    0.61
    ovou
    0.59
    utte
    0.59
    ari
    0.57
    ){
    0.56
    )(\
    0.56
    itet
    0.56
    "，
    0.55
    ्टर
    0.55
    POSITIVE LOGITS
    ки
    0.85
    άν
    0.84
    지
    0.71
    ку
    0.69
    лез
    0.69
    ם
    0.68
    ع
    0.66
    то
    0.65
    ленных
    0.65
    ால
    0.64
    Activations Density 0.015%

    No Known Activations