© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12875
    Prev
    Next
    INDEX
    Explanations

    double-edged sword

    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
    പ്പെടു
    0.37
    WebV
    0.35
     неуда
    0.33
    ürk
    0.33
    ố
    0.33
    șt
    0.33
     createContext
    0.32
    ynamic
    0.32
     கோடி
    0.32
    kości
    0.32
    POSITIVE LOGITS
     double
    2.50
    double
    2.20
     Double
    2.17
    Double
    2.13
     DOUBLE
    1.93
     डबल
    1.91
    双
    1.83
    DOUBLE
    1.79
     двой
    1.77
    雙
    1.71
    Activations Density 0.008%

    No Known Activations