© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27318
    Prev
    Next
    INDEX
    Explanations

    GameMaker Studio 2 or NIH

    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_10_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
    A
    0.68
    ί
    0.67
    し
    0.64
     jeżeli
    0.63
    스러운
    0.63
    ર
    0.63
    রা
    0.62
    றிந்த
    0.62
    した
    0.62
    ियों
    0.62
    POSITIVE LOGITS
    4
    0.91
    5
    0.83
    o
    0.79
    7
    0.73
    9
    0.71
    -
    0.68
     ي
    0.66
     ц
    0.63
    NSW
    0.63
    га
    0.63
    Activations Density 0.000%

    No Known Activations