© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31691
    Prev
    Next
    INDEX
    Explanations

    seizure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    θυ
    0.44
     Sora
    0.41
    ERGY
    0.40
     saj
    0.40
    đena
    0.40
    Rebecca
    0.39
    옇
    0.39
     Buckeye
    0.39
    ედ
    0.39
     büyü
    0.39
    POSITIVE LOGITS
     seizure
    0.44
     Sei
    0.43
     seizing
    0.42
     રો
    0.41
    塞
    0.41
    вня
    0.40
     seized
    0.40
    気軽
    0.40
     MARTIN
    0.39
     Се
    0.38
    Activations Density 0.000%

    No Known Activations