© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43352
    Prev
    Next
    INDEX
    Explanations

    judicial review, Verne, Schwartz, Cesare

    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_3_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
    н
    0.75
    IR
    0.73
     for
    0.69
     Give
    0.69
     RBIs
    0.67
    ン
    0.64
    URA
    0.63
    IA
    0.62
    UD
    0.62
     feb
    0.62
    POSITIVE LOGITS
    માં
    0.75
    ها
    0.68
    신
    0.67
     ಮತ್ತು
    0.64
    álisis
    0.62
    지만
    0.61
     immobil
    0.61
     त्वचा
    0.60
    ಸಾ
    0.60
    مة
    0.59
    Activations Density 0.000%

    No Known Activations