© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206511
    Prev
    Next
    INDEX
    Explanations

    if errors occur

    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_37_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
     когда
    0.58
     inability
    0.57
     lorsque
    0.50
     Когда
    0.50
     when
    0.50
     ketika
    0.49
    當
    0.49
     kiedy
    0.48
     fehl
    0.48
    未能
    0.48
    POSITIVE LOGITS
    Prosecutors
    0.41
    Generally
    0.38
    Compatibility
    0.38
    嘯
    0.37
     უნდა
    0.36
    ಪೆ
    0.36
    पे
    0.36
     SHOULD
    0.36
    Whit
    0.36
    SHO
    0.35
    Activations Density 0.006%

    No Known Activations