© 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. 19228
    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
    Negative Logits
     SHEET
    0.41
    <unused13>
    0.40
     yeux
    0.40
    ্ের
    0.39
    ஷன்
    0.39
     continuum
    0.38
    霢
    0.38
     इंट्रोडक्शन
    0.38
    ρωση
    0.38
     န
    0.38
    POSITIVE LOGITS
    add
    0.39
     add
    0.36
     Slash
    0.36
    Add
    0.36
    Et
    0.35
     Add
    0.34
     pod
    0.34
     вали
    0.33
    かもし
    0.33
    valor
    0.32
    Activations Density 0.000%

    No Known Activations