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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260470
    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
    า
    1.07
    وما
    1.02
    뎐
    1.00
    looms
    0.99
    дал
    0.99
    Programa
    0.95
     விற்ப
    0.94
    েনি
    0.94
    ى
    0.94
    полне
    0.91
    POSITIVE LOGITS
     цветов
    1.15
     aDecoder
    1.11
     ডাক
    1.09
    குரு
    1.06
    큰
    1.04
     comentários
    1.02
     tags
    1.02
    $.}
    1.01
     admired
    1.01
    ive
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.