© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40433
    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_57_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
     afficher
    0.39
    HAND
    0.39
    켜
    0.38
    촤
    0.37
    ilab
    0.37
    ிகை
    0.36
     وقال
    0.36
     масштаб
    0.36
     でしょう
    0.35
    ieke
    0.35
    POSITIVE LOGITS
     Making
    0.41
     MAKING
    0.38
    bor
    0.37
     making
    0.35
     Brent
    0.35
    जेंट
    0.34
     gjort
    0.34
    making
    0.34
    밍
    0.34
    ㄩ
    0.33
    Activations Density 0.000%

    No Known Activations