© 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. 133807
    Prev
    Next
    INDEX
    Explanations

    dupe / dupes

    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
    và
    0.89
    g
    0.88
    da
    0.86
    a
    0.82
    name
    0.80
    Р
    0.80
     Brownian
    0.80
     पाठ्यक्रम
    0.79
    rin
    0.79
    del
    0.79
    POSITIVE LOGITS
    ון
    1.09
    ב
    1.01
    л
    0.99
    وا
    0.98
    ار
    0.92
     to
    0.91
    н
    0.91
    ص
    0.90
    ל
    0.89
    ون
    0.85
    Activations Density 0.000%

    No Known Activations