© 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. 50064
    Prev
    Next
    INDEX
    Explanations

    )

    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
    의
    0.35
    もら
    0.34
    các
    0.33
    a
    0.32
    체의
    0.31
    g
    0.30
    편
    0.30
     населения
    0.30
    ᱖
    0.30
    ده
    0.29
    POSITIVE LOGITS
    ;
    0.37
    ou
    0.36
    (
    0.35
     n
    0.34
    iz
    0.34
    ar
    0.32
    ר
    0.32
    for
    0.31
    ol
    0.31
    lar
    0.31
    Activations Density 0.134%

    No Known Activations