© 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. 133802
    Prev
    Next
    INDEX
    Explanations

    LaTeX tikzpicture diagrams

    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
    akarane
    0.38
    IMPORTED
    0.38
     Manufact
    0.37
     estación
    0.37
     ol
    0.36
    畫
    0.36
    Crud
    0.36
    Acet
    0.35
    擁
    0.35
    कर्ता
    0.35
    POSITIVE LOGITS
     Drivers
    0.42
    Drivers
    0.41
     Tribunal
    0.39
    引擎
    0.39
     exemption
    0.37
    atine
    0.37
     =-\
    0.37
     bittern
    0.37
    EnumValue
    0.37
     driver
    0.36
    Activations Density 0.003%

    No Known Activations