© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257568
    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
    لیت
    1.18
    
    1.04
    ณฑ
    1.04
    gué
    0.95
    >(</
    0.95
     Brim
    0.94
     borderRadius
    0.93
     आखिर
    0.92
    fits
    0.91
    נן
    0.90
    POSITIVE LOGITS
     messo
    1.25
     иссле
    1.24
    嘿
    1.23
     vre
    1.22
     recherches
    1.22
    ড়ন
    1.22
    下次
    1.22
     પ્રમાણે
    1.21
    Как
    1.21
    混乱
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.