© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202725
    Prev
    Next
    INDEX
    Explanations

    running = True

    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_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
     dentistry
    0.45
     degenerate
    0.44
    ಟ್‌
    0.40
    OLYBDENUM
    0.39
    ப்படி
    0.38
     creeps
    0.38
    Ặ
    0.37
     Dentistry
    0.37
    ชีพ
    0.37
     toot
    0.37
    POSITIVE LOGITS
    arm
    0.43
    div
    0.41
     Hanson
    0.37
    ஷா
    0.36
    )}{
    0.36
    isNaN
    0.36
    irm
    0.36
    applications
    0.36
    शा
    0.35
     отношениях
    0.35
    Activations Density 0.001%

    No Known Activations