© 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. 8744
    Prev
    Next
    INDEX
    Explanations

    mixed-use development

    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
    Negative Logits
    ī
    0.26
     bū
    0.26
     به‌
    0.26
    КС
    0.26
     constituent
    0.25
     交換
    0.25
     Не
    0.25
     Patrimonio
    0.25
    کے
    0.25
    кса
    0.25
    POSITIVE LOGITS
    o
    0.28
    هرب
    0.26
     heady
    0.25
    hurst
    0.24
    tions
    0.24
    dung
    0.24
     horsepower
    0.24
    rion
    0.24
    alop
    0.24
    t
    0.24
    Activations Density 0.001%

    No Known Activations