© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63941
    Prev
    Next
    INDEX
    Explanations

    templates

    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_59_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
     á
    0.38
    äger
    0.37
     ó
    0.37
    <0x0D>
    0.37
     ù
    0.35
     noção
    0.34
    </i>
    0.33
    ò
    0.33
     gage
    0.32
     no
    0.32
    POSITIVE LOGITS
    ONA
    0.36
    %；
    0.34
    positroid
    0.33
     ileri
    0.33
     този
    0.32
     Dieser
    0.32
    儆
    0.32
     रहे
    0.31
     этой
    0.31
     этот
    0.31
    Activations Density 0.002%

    No Known Activations