© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26431
    Prev
    Next
    INDEX
    Explanations

    State University or Capitol Building

    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
    ك
    0.95
    ب
    0.78
    }\
    0.77
    几
    0.76
    álló
    0.73
    一部分
    0.73
    个
    0.72
    ..
    0.71
    Permission
    0.71
    2
    0.71
    POSITIVE LOGITS
     divulg
    0.82
     থাকিত
    0.77
    kannya
    0.75
    ut
    0.73
     esper
    0.70
    uje
    0.69
    ہ
    0.68
    ERS
    0.68
     agreg
    0.68
     ya
    0.68
    Activations Density 0.000%

    No Known Activations