© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 140247
    Prev
    Next
    INDEX
    Explanations

    things get

    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_37_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
    ,((
    0.38
    叧
    0.38
    ,(((
    0.38
    事
    0.38
     事
    0.37
     work
    0.36
    work
    0.35
     CEC
    0.34
    ariam
    0.34
     सा
    0.33
    POSITIVE LOGITS
     entusiasmo
    0.38
    čnosti
    0.38
     enthous
    0.38
    vedi
    0.38
     diversión
    0.37
     tia
    0.37
    䂘
    0.37
    гули
    0.36
     हुन
    0.36
     entusi
    0.36
    Activations Density 0.007%

    No Known Activations