© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129482
    Prev
    Next
    INDEX
    Explanations

    <html> <head> <title>

    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_6_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
    ב
    1.16
    는
    1.05
    בח
    1.02
    בק
    0.96
     알려
    0.94
    אם
    0.92
    ಮ
    0.90
    മ
    0.89
    จะไม่
    0.89
    اگر
    0.88
    POSITIVE LOGITS
    s
    1.90
    h
    1.25
    y
    1.14
    <0xA1>
    0.99
    ی
    0.99
     y
    0.93
    en
    0.91
    یی
    0.86
     s
    0.85
    st
    0.85
    Activations Density 0.002%

    No Known Activations