© 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. 30583
    Prev
    Next
    INDEX
    Explanations

    `.com/articles/`

    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
     acute
    0.43
     学生
    0.39
    匝
    0.39
    绉
    0.39
    急性
    0.39
    昃
    0.38
    》。
    0.38
    тился
    0.38
    —.
    0.38
    淀
    0.38
    POSITIVE LOGITS
     protect
    0.38
     vector
    0.38
     rockets
    0.37
    GUAR
    0.37
    ())+
    0.37
     Obl
    0.36
     हेली
    0.36
     helicopters
    0.36
     hawks
    0.36
     vex
    0.35
    Activations Density 0.001%

    No Known Activations