© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4694
    Prev
    Next
    INDEX
    Explanations

    at odds

    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_40_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
     sif
    0.37
     ል
    0.35
    HOP
    0.35
     చిహ్
    0.34
     ساح
    0.34
     سا
    0.33
     बंध
    0.33
     बनेंगे
    0.33
    .$\
    0.33
    หล่ง
    0.33
    POSITIVE LOGITS
     perpendicular
    0.63
     cross
    0.62
    cross
    0.59
     purposes
    0.56
     perpendicularly
    0.56
    CROSS
    0.50
     crossed
    0.50
     perpend
    0.50
     orthogonal
    0.49
     logger
    0.49
    Activations Density 0.090%

    No Known Activations