© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80483
    Prev
    Next
    INDEX
    Explanations

    closing parentheses in method definitions

    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_31_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
     그러니까
    0.38
    studentRecord
    0.37
     unless
    0.37
     fluctuates
    0.36
     exceptions
    0.36
     miscellaneous
    0.36
     kimi
    0.36
    洴
    0.36
    진다
    0.35
    箇所
    0.35
    POSITIVE LOGITS
     উত্স
    0.45
    सिन
    0.40
    ási
    0.35
    coa
    0.35
     dív
    0.34
    rédients
    0.34
     carène
    0.34
     femur
    0.34
    最高
    0.33
    ந்தை
    0.33
    Activations Density 0.001%

    No Known Activations