© 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. 78484
    Prev
    Next
    INDEX
    Explanations

    centro cultural, storico, religioso, american

    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
    ي
    1.39
    在
    1.34
    ﺪ
    1.27
    ία
    1.27
    the
    1.22
    に
    1.22
     в
    1.16
    то
    1.16
    на
    1.14
    ก
    1.14
    POSITIVE LOGITS
    ↵
    1.73
    T
    1.68
     at
    1.31
    ih
    1.30
    n
    1.29
     ibang
    1.28
     on
    1.27
    ow
    1.22
    ut
    1.17
    TER
    1.16
    Activations Density 0.000%

    No Known Activations