© 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. 206839
    Prev
    Next
    INDEX
    Explanations

    express static files

    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
     Lina
    0.39
    Bin
    0.37
    FromJson
    0.37
    ccgi
    0.36
     Bian
    0.36
    PUB
    0.36
    γμα
    0.35
    둔
    0.35
    Filename
    0.35
    Fiscal
    0.35
    POSITIVE LOGITS
     লেখা
    0.44
     electrolysis
    0.42
     electroly
    0.40
     учеб
    0.40
    ocortic
    0.40
    నులు
    0.39
     ইলেকট্র
    0.39
     نبود
    0.39
    軒
    0.39
     मैथ्स
    0.38
    Activations Density 0.001%

    No Known Activations