© 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. 14641
    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
     бк
    0.37
    Writes
    0.31
    bure
    0.30
    ляются
    0.30
    写入
    0.29
     fwrite
    0.29
     grandson
    0.29
     `@
    0.29
     التص
    0.28
    qo
    0.28
    POSITIVE LOGITS
    phone
    0.34
     patho
    0.33
    paths
    0.33
    parts
    0.32
     đặt
    0.32
    sent
    0.31
    dem
    0.30
    Immutable
    0.30
    iate
    0.30
    alte
    0.30
    Activations Density 0.000%

    No Known Activations