© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41051
    Prev
    Next
    INDEX
    Explanations

    the maximum

    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_11_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
    𝗻
    0.64
    یل
    0.62
    प्रमाणे
    0.62
    𝗴
    0.62
    ̣t
    0.62
    께
    0.62
    බන්ධ
    0.61
    чники
    0.61
     postérieures
    0.61
    𝐰
    0.60
    POSITIVE LOGITS
    s
    0.66
    /
    0.63
     وي
    0.63
     can
    0.62
    c
    0.61
    />
    0.60
    }{
    0.59
    ;/
    0.59
    .>
    0.58
    >*
    0.57
    Activations Density 0.015%

    No Known Activations