© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195522
    Prev
    Next
    INDEX
    Explanations

    semantic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     uter
    0.40
    Teaching
    0.39
    ेज
    0.38
    тю
    0.38
    ቃ
    0.38
    Ces
    0.38
     Ces
    0.37
    attie
    0.37
    ⸨
    0.37
    Unis
    0.36
    POSITIVE LOGITS
     handen
    0.38
    elapse
    0.36
     Supp
    0.36
    ່
    0.36
     Response
    0.35
     admissible
    0.35
     powst
    0.35
    WriteLine
    0.35
     Supper
    0.34
     superscript
    0.34
    Activations Density 0.000%

    No Known Activations