© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201482
    Prev
    Next
    INDEX
    Explanations

    cially

    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_46_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
     mainland
    0.40
     വര
    0.39
    置
    0.39
     проблему
    0.38
    BLE
    0.38
    죽
    0.38
    ble
    0.37
     Alcoholic
    0.37
    姑
    0.37
     Mainland
    0.37
    POSITIVE LOGITS
     important
    0.70
    important
    0.65
     vigt
    0.64
     importantes
    0.63
     penting
    0.63
     importanti
    0.62
     مهم
    0.60
    Important
    0.60
    重要的
    0.59
     importants
    0.59
    Activations Density 0.003%

    No Known Activations