© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91560
    Prev
    Next
    INDEX
    Explanations

    storm surge

    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_3_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
    in
    1.30
    م
    1.07
    is
    0.94
    ي
    0.93
    ت
    0.84
    м
    0.84
    د
    0.83
    i
    0.79
    ف
    0.77
    ن
    0.77
    POSITIVE LOGITS
    arı
    0.70
     Been
    0.56
    কিন্ত
    0.55
    枒
    0.55
    خدم
    0.55
    ະພັນ
    0.54
    鉆
    0.53
     হুঁ
    0.53
    ер
    0.52
    ْم
    0.52
    Activations Density 0.000%

    No Known Activations