© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 206109
    Prev
    Next
    INDEX
    Explanations

    seconds concentric (lifting), 1 second hold

    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_25_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
    椛
    0.37
     다음
    0.34
    ܸ
    0.34
     باید
    0.34
     平成
    0.34
     ശരീ
    0.34
     кандида
    0.34
    Sistema
    0.33
    파
    0.33
    ט
    0.32
    POSITIVE LOGITS
     worded
    0.31
    highest
    0.29
     林
    0.29
     Highest
    0.28
     wording
    0.27
     highest
    0.27
    ूंकि
    0.27
     serpentine
    0.27
    lowest
    0.27
     Несмотря
    0.27
    Activations Density 0.001%

    No Known Activations