© 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. 17628
    Prev
    Next
    INDEX
    Explanations

    scholar, exam, imperial China

    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
     ধর্ম
    0.42
     религи
    0.42
     Relig
    0.40
     thủy
    0.39
     religi
    0.38
     Devon
    0.38
     बालकनियां
    0.38
    葦
    0.38
    狒
    0.38
    ञ्च
    0.37
    POSITIVE LOGITS
     scholarly
    0.55
    schol
    0.54
     scholar
    0.52
     scholars
    0.52
     exam
    0.49
     Scholars
    0.49
    Exam
    0.48
     Scholar
    0.46
     Exam
    0.46
    exam
    0.44
    Activations Density 0.017%

    No Known Activations