Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165878
    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_13_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
    鶚
    0.48
    ভোগ
    0.47
    OnUiThread
    0.45
     Ekim
    0.44
    Кто
    0.44
     بشكل
    0.43
    <unused538>
    0.43
    Skin
    0.43
    גם
    0.43
    љено
    0.43
    POSITIVE LOGITS
    h
    0.54
    an
    0.49
    class
    0.48
    on
    0.48
    all
    0.48
    '*
    0.48
    product
    0.47
    parse
    0.47
    cl
    0.47
    v
    0.47
    Activations Density 0.000%

    No Known Activations