© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54954
    Prev
    Next
    INDEX
    Explanations

    shuffle = true

    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_30_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
    恙
    0.42
    imamente
    0.38
     सय
    0.38
     zone
    0.38
     wandering
    0.37
     picturesque
    0.37
     zonas
    0.37
     wander
    0.37
    ेंसी
    0.36
     fortaleza
    0.36
    POSITIVE LOGITS
    isati
    0.37
     انھوں
    0.36
    Larg
    0.35
     مخ
    0.35
    askell
    0.35
    厙
    0.35
    item
    0.35
    istä
    0.34
    ubern
    0.34
     Morgan
    0.34
    Activations Density 0.000%

    No Known Activations