© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199721
    Prev
    Next
    INDEX
    Explanations

    code construction, function arguments

    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_27_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
     женщины
    0.41
     ошибка
    0.39
     женщин
    0.39
     зло
    0.38
     жінок
    0.38
    弾
    0.38
    彈
    0.37
    방
    0.37
     `
    0.36
     đáo
    0.36
    POSITIVE LOGITS
    شركة
    0.45
    𝚟
    0.44
     exame
    0.42
    वृद्धि
    0.42
    Ბ
    0.42
     semnific
    0.41
     സൂ
    0.40
     comportamiento
    0.40
    भा
    0.40
     crescimento
    0.39
    Activations Density 0.000%

    No Known Activations