© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24700
    Prev
    Next
    INDEX
    Explanations

    code or programming

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    \$
    0.50
    лен
    0.47
    Ś
    0.43
    чет
    0.42
    ­
    0.42
    place
    0.42
    \#
    0.41
    $
    0.41
    č
    0.41
    Č
    0.41
    POSITIVE LOGITS
     继续访问
    0.39
     သည်
    0.37
     例如
    0.37
    </em>
    0.36
    」、
    0.36
     阅读全文
    0.35
    Continue
    0.34
     ​
    0.34
    boBox
    0.34
     率
    0.34
    Activations Density 0.164%

    No Known Activations