© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241312
    Prev
    Next
    INDEX
    Explanations

    animals

    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_40_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
     ফেলেছে
    0.34
     স্থায়ী
    0.33
     апо
    0.33
     આપે
    0.32
     한다
    0.32
    ysuckle
    0.31
     ফেলেছেন
    0.31
    𝐦
    0.30
     সেট
    0.29
     सुने
    0.29
    POSITIVE LOGITS
    ご覧
    0.39
     readability
    0.33
    ้อ
    0.33
    graphics
    0.32
     Symmetric
    0.32
    矩
    0.31
    绘
    0.30
     graphics
    0.30
    开放
    0.30
    矾
    0.30
    Activations Density 0.001%

    No Known Activations