© 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. 26746
    Prev
    Next
    INDEX
    Explanations

    code loop indices

    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
     stanow
    0.43
     vé
    0.42
    ینده
    0.41
     system
    0.40
    defined
    0.39
     defined
    0.38
    >{</
    0.38
     relaxation
    0.38
     textSize
    0.37
     consens
    0.37
    POSITIVE LOGITS
     বাংলাদেশী
    0.39
    groupby
    0.38
    老
    0.37
    ილ
    0.36
    itian
    0.36
     އެ
    0.36
     அட்ட
    0.36
    슭
    0.36
    等が
    0.34
    !)
    0.34
    Activations Density 0.003%

    No Known Activations