© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90195
    Prev
    Next
    INDEX
    Explanations

    font style assignment

    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_23_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
    ellation
    0.38
     മനു
    0.38
    emiah
    0.38
    тово
    0.37
     proble
    0.37
     universo
    0.37
     ocean
    0.37
    щення
    0.36
     молоды
    0.36
    稜
    0.36
    POSITIVE LOGITS
     fatality
    0.42
     Adapter
    0.41
    ->
    0.40
     deps
    0.40
     गेम
    0.39
    
    0.39
     Seasons
    0.39
     Daughter
    0.38
     doses
    0.37
     roles
    0.37
    Activations Density 0.001%

    No Known Activations