© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14999
    Prev
    Next
    INDEX
    Explanations

    centering elements

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ющие
    0.53
    ش
    0.50
    фото
    0.50
    Luis
    0.47
    roqu
    0.47
    ividade
    0.46
    RowFilter
    0.46
    дений
    0.45
     Gutiérrez
    0.44
    дию
    0.44
    POSITIVE LOGITS
     vsize
    0.52
    対
    0.46
     acetylation
    0.46
    iteten
    0.45
    četně
    0.44
     Tuscany
    0.43
    veys
    0.43
     wakeup
    0.43
    easter
    0.43
    CENTR
    0.42
    Activations Density 0.058%

    No Known Activations