© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81346
    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_31_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
     Pais
    0.38
     গৃহে
    0.37
     Ring
    0.36
    提
    0.36
     Kanton
    0.35
    齒
    0.35
    肓
    0.35
     lac
    0.35
     paintings
    0.34
     corrosion
    0.34
    POSITIVE LOGITS
    WAL
    0.38
     walked
    0.38
    Wald
    0.38
     (\$
    0.37
    刻
    0.37
    imli
    0.36
    left
    0.36
    ribut
    0.36
    eek
    0.36
    粆
    0.36
    Activations Density 0.000%

    No Known Activations