© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78472
    Prev
    Next
    INDEX
    Explanations

    uros, os, 浏览器

    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_0_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
    กัน
    1.41
    ing
    1.24
    ↵↵
    1.14
     and
    1.13
     decentral
    1.13
    olds
    1.12
    izers
    1.05
    ते
    0.99
     industrialized
    0.97
    ised
    0.94
    POSITIVE LOGITS
    та
    1.60
    ت
    1.60
    dır
    1.47
    ться
    1.39
    т
    1.38
    IN
    1.38
    ي
    1.34
    ิ
    1.34
    مي
    1.27
    jší
    1.26
    Activations Density 0.000%

    No Known Activations