© 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
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64052
    Prev
    Next
    INDEX
    Explanations

    current status and estimates

    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_41_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
     sitting
    2.61
     sit
    2.59
     sits
    2.42
     Sitting
    2.42
    Sitting
    2.42
    Sit
    2.39
    坐
    2.34
    sitting
    2.31
     Sit
    2.28
     sitzen
    2.20
    POSITIVE LOGITS
    樎
    0.38
     Insol
    0.37
    бри
    0.37
     Substance
    0.37
     Maker
    0.35
    zei
    0.35
     支持
    0.34
     cheating
    0.34
    omile
    0.33
     ট্যাঙ্ক
    0.33
    Activations Density 0.018%

    No Known Activations