© 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. 247539
    Prev
    Next
    INDEX
    Explanations

    specification version 1.0

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Wolfgang
    0.31
    拠
    0.30
     envis
    0.30
     straps
    0.29
    ashions
    0.29
     cüm
    0.29
     कोरबा
    0.29
    討論
    0.28
    ૌ
    0.28
    營養
    0.28
    POSITIVE LOGITS
     réc
    0.36
    izielle
    0.36
     tipo
    0.35
     रिकार्ड
    0.33
     representa
    0.32
    type
    0.32
    товые
    0.31
     Class
    0.31
     শিক
    0.31
     Cada
    0.31
    Activations Density 0.002%

    No Known Activations