© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212461
    Prev
    Next
    INDEX
    Explanations

    computing and calculating mathematical operations

    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_19_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
    ส์
    0.39
     using
    0.38
     retrospective
    0.37
    ְ
    0.37
     comet
    0.35
     declaration
    0.35
    اسی
    0.35
     use
    0.35
     competition
    0.35
     preliminary
    0.34
    POSITIVE LOGITS
     `'\\
    0.37
    𒊒
    0.36
    IRQHandler
    0.34
     시장
    0.33
    ቱም
    0.33
    🍐
    0.33
     القناه
    0.33
    Leader
    0.32
    Ꮤ
    0.32
    _',
    0.32
    Activations Density 0.002%

    No Known Activations