© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83114
    Prev
    Next
    INDEX
    Explanations

    import

    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_53_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
    
    0.43
    
    0.39
    хин
    0.38
    ನನ್ನು
    0.38
    Sky
    0.38
    /**/*.{
    0.38
    ﹙
    0.37
     виду
    0.37
    त्रा
    0.37
    }({\
    0.36
    POSITIVE LOGITS
     Byron
    0.40
    wają
    0.38
    रित
    0.38
     Ehr
    0.37
    eu
    0.36
    iou
    0.35
    oresis
    0.35
    മ്പോള്‍
    0.35
    iol
    0.34
    பாய்
    0.34
    Activations Density 0.001%

    No Known Activations