© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237248
    Prev
    Next
    INDEX
    Explanations

    types of vision

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    સા
    0.40
    ائِ
    0.40
     forfeit
    0.38
     surrender
    0.37
    Validator
    0.36
     श्रा
    0.36
    ñoz
    0.35
    Apr
    0.35
    ulado
    0.35
    默
    0.35
    POSITIVE LOGITS
     E
    0.37
     περισ
    0.37
     пя
    0.37
    鳕
    0.36
    idE
    0.36
    ⑸
    0.35
     १५
    0.35
     expiresIn
    0.35
    彊
    0.35
    र्में
    0.34
    Activations Density 0.017%

    No Known Activations