© 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. 139952
    Prev
    Next
    INDEX
    Explanations

    code map and update

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Lag
    0.40
    愕
    0.38
    OPERATION
    0.38
    imab
    0.36
    щина
    0.35
     character
    0.35
    Forces
    0.35
     chiaro
    0.34
     INDUSTRY
    0.34
    ânea
    0.34
    POSITIVE LOGITS
     প্য
    0.41
    矶
    0.39
    cwd
    0.38
     Kare
    0.37
    iziModal
    0.37
    阮
    0.37
     رولی
    0.36
     flares
    0.36
     funcionario
    0.36
     lar
    0.36
    Activations Density 0.000%

    No Known Activations