© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30163
    Prev
    Next
    INDEX
    Explanations

    wr `.png`, WRatio, WEF, WGSL

    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_10_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
    an
    0.89
    𝑤
    0.83
    ä
    0.82
    ab
    0.82
    AY
    0.80
    ethe
    0.80
    ે
    0.79
    ેર
    0.76
    ou
    0.75
    жета
    0.75
    POSITIVE LOGITS
    ش
    1.02
     that
    0.96
    时间
    0.90
    ن
    0.90
    也
    0.87
    ס
    0.86
    אי
    0.86
    తో
    0.80
    高
    0.79
    </h3>
    0.79
    Activations Density 0.017%

    No Known Activations