© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259991
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
     wonderful
    1.14
    ק
    1.14
     Wonderful
    1.04
    ik
    1.01
     wondrous
    0.99
    ال
    0.97
     phenomenal
    0.97
    ار
    0.95
    <bos>
    0.93
     wilayah
    0.90
    POSITIVE LOGITS
     salida
    1.42
     obliga
    1.35
     probl
    1.31
    滚
    1.29
    ません
    1.28
    滾
    1.27
     flourishes
    1.25
     dvi
    1.25
     आकांक्षा
    1.25
     cuch
    1.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.