© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205845
    Prev
    Next
    INDEX
    Explanations

    go to a location

    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_6_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
    ItemStack
    0.79
     않았
    0.76
    RectangleShape
    0.71
    Anime
    0.71
    Einzel
    0.71
    Annotations
    0.71
    Parser
    0.69
    $
    0.68
    Você
    0.67
    Appending
    0.67
    POSITIVE LOGITS
    s
    1.79
    on
    1.29
    y
    1.27
    ي
    1.18
    b
    1.15
    es
    1.11
    i
    1.11
    in
    1.09
    t
    1.07
    d
    1.07
    Activations Density 0.003%

    No Known Activations