© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8849
    Prev
    Next
    INDEX
    Explanations

    Here's a breakdown

    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_13_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
     навча
    0.39
    İK
    0.39
    cretsiz
    0.38
    ції
    0.37
     ehemalige
    0.37
    闾
    0.36
     의료
    0.36
     اگلے
    0.36
    Ꮮ
    0.36
    achricht
    0.36
    POSITIVE LOGITS
    Type
    0.34
    umento
    0.32
    Suppose
    0.31
    Didn
    0.31
    Doesn
    0.31
        
    0.31
    Through
    0.31
    之人
    0.30
    Annual
    0.30
    Tiene
    0.30
    Activations Density 0.112%

    No Known Activations