© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210091
    Prev
    Next
    INDEX
    Explanations

    Head of / Headspace

    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_5_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
    ج
    1.54
    ח
    1.54
    ى
    1.49
    ק
    1.47
    ین
    1.43
    ي
    1.41
    ס
    1.39
    ال
    1.30
    اس
    1.26
    ाल
    1.25
    POSITIVE LOGITS
    ’
    1.57
    '
    1.55
    B
    1.02
    š
    0.99
    ﺼ
    0.96
    em
    0.88
    `
    0.88
    能力
    0.88
    க்கும்
    0.87
    起床
    0.87
    Activations Density 0.021%

    No Known Activations