© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24044
    Prev
    Next
    INDEX
    Explanations

    grab, snatch, take

    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_10_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
    ك
    0.96
    ка
    0.91
    1
    0.83
     as
    0.78
     و
    0.73
    ch
    0.67
    kha
    0.64
    k
    0.63
     وال
    0.62
    tic
    0.62
    POSITIVE LOGITS
     сообщи
    0.93
     взя
    0.90
    ınız
    0.83
    ა
    0.83
    एम
    0.82
     powied
    0.81
     rozpoczę
    0.81
     Gather
    0.80
    '।
    0.79
    anız
    0.79
    Activations Density 0.010%

    No Known Activations