© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7604
    Prev
    Next
    INDEX
    Explanations

    python version numbers

    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_39_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
    اتي
    0.32
    醂
    0.32
    Pe
    0.32
    -​
    0.32
     перечис
    0.32
    Python
    0.31
    ​]]
    0.31
    .​​
    0.31
    
    0.30
    ​​​​
    0.30
    POSITIVE LOGITS
     surge
    0.40
     surging
    0.36
     aboard
    0.34
     niente
    0.33
     fra
    0.33
    journ
    0.33
     freeze
    0.32
     ло
    0.32
    lö
    0.32
     berätt
    0.32
    Activations Density 0.018%

    No Known Activations