© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180334
    Prev
    Next
    INDEX
    Explanations

    I Logger, Configuration, Product

    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_24_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
     जल्द
    0.38
    odb
    0.38
     '=',
    0.38
    헛
    0.38
    soon
    0.38
    נ
    0.38
     Vav
    0.37
     ആയി
    0.37
    ಿದೆ
    0.36
     शीघ्र
    0.36
    POSITIVE LOGITS
     filtr
    0.46
    澜
    0.39
     මො
    0.38
    狲
    0.38
     زمانے
    0.38
    瀾
    0.37
     সেখানকার
    0.37
     DEALINGS
    0.36
    钦
    0.36
     வடிக
    0.36
    Activations Density 0.000%

    No Known Activations