© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57518
    Prev
    Next
    INDEX
    Explanations

    ci

    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_11_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
    en
    0.73
    es
    0.72
    for
    0.68
    Passengers
    0.68
    Able
    0.68
    HOW
    0.67
    জ
    0.66
    FOR
    0.64
    Format
    0.64
    ;}
    0.64
    POSITIVE LOGITS
    кий
    0.68
    ական
    0.68
    '
    0.64
    istiche
    0.64
     Reel
    0.63
    <0x89>
    0.61
    gård
    0.60
     Pumpkin
    0.59
     Ecuadorian
    0.59
    мати
    0.59
    Activations Density 0.012%

    No Known Activations