© 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. 206722
    Prev
    Next
    INDEX
    Explanations

    downloading and installing software

    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
    计算机
    0.38
    FileData
    0.38
     BOU
    0.38
     computadora
    0.37
    FileLine
    0.36
    悬
    0.35
    Bou
    0.34
    illing
    0.34
    ,​
    0.34
     normalised
    0.34
    POSITIVE LOGITS
     Facebook
    0.42
     eBay
    0.40
     paint
    0.39
     https
    0.39
    ได้
    0.39
     сайте
    0.39
    https
    0.38
    ೆಂಟ್
    0.38
    RETURNTRANSFER
    0.38
    Facebook
    0.38
    Activations Density 0.010%

    No Known Activations