© 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. 144170
    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
    ,
    0.91
    ذا
    0.88
    ről
    0.77
    ουν
    0.75
    ையில்
    0.72
    裘
    0.71
    ੀ
    0.71
     сохра
    0.69
    もら
    0.68
    స్‌
    0.68
    POSITIVE LOGITS
    '
    1.23
     it
    1.14
     are
    1.11
     can
    1.02
    न
    0.98
    ন
    0.97
     have
    0.96
    ν
    0.95
    is
    0.90
    ن
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.