© 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. 259983
    Prev
    Next
    INDEX
    Explanations

    trade-in value, options, discounts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    tiempo
    0.91
    Tiempo
    0.86
    WithName
    0.81
    entire
    0.81
    geometric
    0.75
    goatee
    0.74
    SqlCommand
    0.74
    ڌ
    0.74
    NuGet
    0.73
    duration
    0.72
    POSITIVE LOGITS
     Betty
    0.73
     reflex
    0.73
     Text
    0.72
     রকম
    0.70
     Voltaire
    0.69
     Judy
    0.69
     Julie
    0.69
    Judy
    0.67
     환
    0.67
     Sophia
    0.66
    Activations Density 0.001%

    No Known Activations