© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61008
    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_2_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
    an
    1.63
    a
    1.48
    ０
    1.18
    0
    1.17
    ۰
    1.09
    '
    1.09
    ០
    1.02
    aVal
    0.91
     ν
    0.90
    
    0.89
    POSITIVE LOGITS
    س
    1.93
    ק
    1.54
    ב
    1.38
    ל
    1.34
    ס
    1.33
    เป็น
    1.32
    ת
    1.32
    یا
    1.27
    ب
    1.25
    نا
    1.24
    Activations Density 0.000%

    No Known Activations