© 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. 54945
    Prev
    Next
    INDEX
    Explanations

    index `i]`

    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
    交给
    0.39
     iluminación
    0.37
     análisis
    0.37
     ዳ
    0.35
     කරන
    0.35
    pyridin
    0.34
     каждым
    0.34
     tasarım
    0.34
     анализ
    0.33
     جانتے
    0.33
    POSITIVE LOGITS
    min
    0.33
     minima
    0.33
    lim
    0.33
     blitz
    0.32
     minimale
    0.32
    쩡
    0.32
     pl
    0.32
     smooth
    0.31
     hundred
    0.31
    zeit
    0.31
    Activations Density 0.006%

    No Known Activations