© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44090
    Prev
    Next
    INDEX
    Explanations

    Capri, Capybara, CapEx, Cape Cod

    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_3_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
    ের
    0.96
    س
    0.91
    0
    0.83
    স
    0.78
    д
    0.76
    ב
    0.75
    ہ
    0.75
    ０
    0.71
    ט
    0.70
    ים
    0.69
    POSITIVE LOGITS
    n
    1.26
    '
    1.03
    _
    0.95
    w
    0.89
    l
    0.88
    ’
    0.88
    ar
    0.79
    oe
    0.78
    ot
    0.77
    on
    0.77
    Activations Density 0.006%

    No Known Activations