© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56374
    Prev
    Next
    INDEX
    Explanations

    ```json

    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_11_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
    杫
    0.57
     exfoli
    0.53
    篾
    0.52
     އެ
    0.52
     emuls
    0.50
    ﻭ
    0.50
     protéines
    0.50
     られ
    0.49
     ถ้า
    0.49
    ="#
    0.48
    POSITIVE LOGITS
    com
    0.54
    et
    0.52
    จิต
    0.49
    u
    0.49
     basso
    0.45
    α
    0.43
     Guardia
    0.43
    ولات
    0.42
    天堂
    0.42
    λό
    0.41
    Activations Density 0.009%

    No Known Activations