© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47071
    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_13_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
     COLUMN
    0.51
     פּ
    0.49
    ਰ
    0.49
     Lö
    0.49
     {}".
    0.48
     blower
    0.48
     тощо
    0.48
     trombone
    0.47
    منٹ
    0.47
     pencil
    0.47
    POSITIVE LOGITS
     stateless
    0.54
    ష్
    0.51
    тивными
    0.50
    嵯
    0.50
    ISTA
    0.49
    sinh
    0.49
    лни
    0.48
    fireplace
    0.48
    IST
    0.48
    ෂ්
    0.48
    Activations Density 0.000%

    No Known Activations