© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104185
    Prev
    Next
    INDEX
    Explanations

    cheat sheet or beat sheet

    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_1_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
     for
    0.75
    int
    0.75
     Đại
    0.73
    ب
    0.72
    te
    0.69
    ográf
    0.68
    nels
    0.67
     zahlen
    0.67
    侎
    0.66
    坵
    0.66
    POSITIVE LOGITS
    ва
    0.80
    ו
    0.74
    л
    0.72
    ید
    0.71
    з
    0.70
    ль
    0.69
    یت
    0.67
    یده
    0.67
    a
    0.67
     ولی
    0.66
    Activations Density 0.000%

    No Known Activations