© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1751
    Prev
    Next
    INDEX
    Explanations

    is essential or for consult

    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_39_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
    comfortable
    0.31
    春天
    0.30
     استف
    0.30
    たる
    0.30
     IW
    0.29
    ritable
    0.29
     ویس
    0.29
    枫
    0.29
    缙
    0.29
    蕗
    0.29
    POSITIVE LOGITS
     Untuk
    0.35
     skulls
    0.35
     Benin
    0.34
     gourd
    0.34
     For
    0.34
     genel
    0.34
     السود
    0.33
     için
    0.33
     สำหรับ
    0.33
     Sudan
    0.32
    Activations Density 0.032%

    No Known Activations