© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1935
    Prev
    Next
    INDEX
    Explanations

    temperature ranges

    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_40_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
     elliptical
    0.30
    떡
    0.28
    পাঁ
    0.28
    ੭
    0.27
     subconsciously
    0.27
    붉
    0.27
     vork
    0.27
    ppy
    0.26
    $",
    0.26
    اں
    0.26
    POSITIVE LOGITS
     للمعارف
    0.32
    体制
    0.31
    Компания
    0.31
    Native
    0.29
     عرف
    0.29
    PROGRESS
    0.29
     गुलाब
    0.28
     dilation
    0.28
     இன்ன
    0.28
    龄
    0.28
    Activations Density 0.006%

    No Known Activations