© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142291
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
     aziende
    0.64
     começar
    0.57
    ૦
    0.57
    a
    0.56
     deserial
    0.55
    же
    0.54
     chiamato
    0.54
     emptied
    0.53
    كان
    0.52
    يجي
    0.52
    POSITIVE LOGITS
    aj
    0.57
    uh
    0.55
     வழி
    0.55
     ه
    0.54
     prioritize
    0.53
     бы
    0.52
     lot
    0.51
    হইবে
    0.51
    hat
    0.50
     همه
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.