© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26663
    Prev
    Next
    INDEX
    Explanations

    epsilon (ε) and related mathematical symbols

    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
    тка
    0.83
    at
    0.81
    ам
    0.79
    é
    0.78
     by
    0.77
    Y
    0.77
    ↵↵
    0.77
    de
    0.76
    दिन
    0.76
    리
    0.75
    POSITIVE LOGITS
     navegador
    0.83
     הם
    0.82
     usato
    0.78
     названия
    0.72
     название
    0.70
     encontr
    0.70
    ]."
    0.70
     جوړونکی
    0.69
    ுள்ளனர்
    0.69
     hablar
    0.68
    Activations Density 0.001%

    No Known Activations