© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11579
    Prev
    Next
    INDEX
    Explanations

    source command `.` or `rc` files

    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_13_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
    ски
    0.52
    েনি
    0.52
    ли
    0.51
    ς
    0.49
    ем
    0.48
    s
    0.48
    κης
    0.48
     এডিনবার্গ
    0.47
    em
    0.47
     cosines
    0.46
    POSITIVE LOGITS
     cierre
    0.61
     개발
    0.57
    မျက်
    0.57
     regurg
    0.55
     각종
    0.54
    💵
    0.54
     कार्य
    0.53
     combustível
    0.53
     ngày
    0.52
     விலை
    0.52
    Activations Density 0.007%

    No Known Activations