© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41567
    Prev
    Next
    INDEX
    Explanations

    hostname, symbol, df, image

    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_22_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
    ="#"><
    0.44
    obucket
    0.44
     éc
    0.41
    conexion
    0.41
    ozat
    0.41
     Ах
    0.40
    crum
    0.39
    ♭
    0.39
     Figueroa
    0.38
     Clément
    0.38
    POSITIVE LOGITS
     এরূপ
    0.42
     этих
    0.41
    PDE
    0.40
    тельных
    0.39
     tasse
    0.39
    త్ప
    0.39
     teeth
    0.38
    pct
    0.38
     appeared
    0.37
     contractile
    0.37
    Activations Density 0.003%

    No Known Activations