© 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. 11537
    Prev
    Next
    INDEX
    Explanations

    locations and entities

    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
    ং
    0.39
    rát
    0.38
     மீன
    0.36
     señ
    0.35
    मित्व
    0.35
    両
    0.34
    ਰ
    0.34
     സ
    0.34
    $};
    0.34
    িন
    0.34
    POSITIVE LOGITS
    ?!
    0.40
    *
    0.37
     basketball
    0.37
    !
    0.36
    ందని
    0.36
    basketball
    0.36
     বিশ্ববিদ্যালয়ে
    0.36
     vm
    0.35
     Pinnacle
    0.35
     __________
    0.35
    Activations Density 0.011%

    No Known Activations