© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83842
    Prev
    Next
    INDEX
    Explanations

    reader context

    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_23_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
     come
    0.40
     recur
    0.37
     تعاون
    0.37
     tre
    0.37
     쇼
    0.36
     thoát
    0.36
    有一天
    0.36
     Obrigado
    0.36
     besoin
    0.36
     sho
    0.36
    POSITIVE LOGITS
     выгляд
    0.44
    erview
    0.41
    ocos
    0.40
    𝑁
    0.39
    escens
    0.38
    step
    0.38
     forceps
    0.38
    เข้าใจ
    0.38
    扼
    0.37
     cakkh
    0.36
    Activations Density 0.002%

    No Known Activations