© 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. 14350
    Prev
    Next
    INDEX
    Explanations

    new project

    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
    ーム
    0.41
    рма
    0.40
    étale
    0.37
    arma
    0.35
    arme
    0.35
    itung
    0.34
    éb
    0.34
    anedi
    0.34
    Ⲱ
    0.33
     Shik
    0.32
    POSITIVE LOGITS
     new
    2.48
    new
    2.17
     নতুন
    2.14
     новый
    2.00
     нового
    1.97
     nueva
    1.95
     новой
    1.95
     новую
    1.94
     nieuwe
    1.92
     новом
    1.91
    Activations Density 0.059%

    No Known Activations