© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19553
    Prev
    Next
    INDEX
    Explanations

    non-negotiable

    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_15_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
    DIA
    0.50
    DVD
    0.49
     bhuv
    0.49
     भुव
    0.48
     fgets
    0.48
    InOut
    0.47
    DIC
    0.47
     {}>,
    0.47
    ята
    0.46
    гол
    0.46
    POSITIVE LOGITS
     numerous
    0.57
    chee
    0.54
     even
    0.54
     allowed
    0.52
    man
    0.52
    чные
    0.52
     man
    0.51
    em
    0.51
     nova
    0.51
     उद्यान
    0.50
    Activations Density 0.013%

    No Known Activations