© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90142
    Prev
    Next
    INDEX
    Explanations

    law and sides

    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_3_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
    ad
    0.88
    ال
    0.86
    ق
    0.83
    يد
    0.82
    id
    0.73
    ↵↵
    0.71
    ला
    0.70
    ס
    0.69
     baggy
    0.66
    फ
    0.66
    POSITIVE LOGITS
    '
    0.97
    ের
    0.84
    the
    0.68
    beqz
    0.68
    -
    0.67
    ים
    0.66
    ों
    0.64
    '<
    0.62
    
    0.61
    ség
    0.59
    Activations Density 0.009%

    No Known Activations