© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87411
    Prev
    Next
    INDEX
    Explanations

    file extensions

    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_23_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
     December
    0.44
    ong
    0.41
    Th
    0.39
     ؛
    0.38
     occasionally
    0.38
    Method
    0.37
     generalized
    0.37
    M
    0.37
     September
    0.37
    insertion
    0.36
    POSITIVE LOGITS
     ശക്തി
    0.46
    퀘
    0.42
    קת
    0.40
    互動
    0.40
     পানি
    0.39
     пане
    0.39
     Indie
    0.38
     freelancer
    0.38
    꼰
    0.38
    лей
    0.37
    Activations Density 0.000%

    No Known Activations