© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205549
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    習
    0.44
    andung
    0.39
    绕
    0.38
     Uncle
    0.37
     кръ
    0.37
     Спа
    0.37
     Ради
    0.37
    Arithmetic
    0.36
    軌
    0.36
    行
    0.36
    POSITIVE LOGITS
     timelapse
    0.43
    rews
    0.41
     feedwater
    0.40
     exposureButton
    0.40
     @_
    0.39
    枒
    0.38
     BrowserWindow
    0.38
     Broughton
    0.38
    啁
    0.38
     subcluster
    0.37
    Activations Density 0.000%

    No Known Activations