© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81051
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    一
    2.17
    ，
    1.79
    s
    1.69
    O
    1.67
    한
    1.66
    家
    1.63
    个
    1.53
    ي
    1.50
    he
    1.48
    IE
    1.48
    POSITIVE LOGITS
    к
    1.47
    تری
    1.35
    ır
    1.31
    м
    1.31
    тся
    1.30
    ﺪ
    1.28
     ی
    1.27
    нення
    1.27
    ین
    1.26
    ه‌های
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.