© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18334
    Prev
    Next
    INDEX
    Explanations

    non-capturing groups

    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_40_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
    ICKEL
    0.39
    Pont
    0.38
    SP
    0.38
    COD
    0.38
    ější
    0.37
     背
    0.37
    ิ้ง
    0.36
    哏
    0.36
     нож
    0.36
    יה
    0.36
    POSITIVE LOGITS
    othesis
    0.42
     restoration
    0.42
     Restore
    0.41
     Ether
    0.40
     diny
    0.40
     paroles
    0.39
     restore
    0.39
    粔
    0.38
     Environment
    0.38
     "?
    0.38
    Activations Density 0.001%

    No Known Activations