© 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. 4646
    Prev
    Next
    INDEX
    Explanations

    reading files

    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
     write
    1.92
     Write
    1.77
     writes
    1.77
    write
    1.71
    Write
    1.71
     writing
    1.66
    写
    1.63
     Writing
    1.57
    寫
    1.57
     WRITE
    1.55
    POSITIVE LOGITS
     reading
    0.70
    阅读
    0.68
    読
    0.67
     đọc
    0.66
    読んで
    0.65
    reading
    0.65
    读取
    0.64
    読む
    0.64
    Reading
    0.63
    閱讀
    0.62
    Activations Density 0.277%

    No Known Activations