© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13119
    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_40_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
    Послед
    0.38
    বিশিষ্ট
    0.37
     Fire
    0.35
     Plut
    0.34
     brightest
    0.34
    uent
    0.34
    Jeff
    0.34
    湧
    0.34
     bato
    0.33
     फायर
    0.32
    POSITIVE LOGITS
     catalytic
    0.42
     ಕ್ಷ
    0.39
     forgiven
    0.37
     subheading
    0.36
     อายุ
    0.36
     Rosa
    0.35
     ith
    0.35
     அவ
    0.35
    ávy
    0.35
    Rosa
    0.35
    Activations Density 0.000%

    No Known Activations