© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133752
    Prev
    Next
    INDEX
    Explanations

    Python Flask API code

    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_37_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
     Blanche
    0.39
    िनेट
    0.36
    corruption
    0.36
    ibration
    0.35
    楞
    0.34
     блоков
    0.34
    ковое
    0.34
    াতে
    0.33
    ोबर
    0.33
    обще
    0.33
    POSITIVE LOGITS
     deseas
    0.40
     cedar
    0.38
     productos
    0.37
     ced
    0.37
    增
    0.37
    डेजा
    0.36
     tle
    0.36
    যন্ত্র
    0.36
    queta
    0.36
     desea
    0.35
    Activations Density 0.000%

    No Known Activations