© 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. 29748
    Prev
    Next
    INDEX
    Explanations

    Australia, Western Australia

    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
    ы
    0.37
    ی
    0.34
    𝙮
    0.32
     файлов
    0.30
     productos
    0.29
     producto
    0.29
     осигура
    0.29
     usuarios
    0.29
     abrir
    0.29
     lectura
    0.29
    POSITIVE LOGITS
    $(
    0.33
    lang
    0.32
    <
    0.32
    g
    0.32
    data
    0.31
    vollen
    0.31
    diag
    0.30
    -'
    0.30
    type
    0.30
    struct
    0.30
    Activations Density 0.006%

    No Known Activations