© 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. 257765
    Prev
    Next
    INDEX
    Explanations

    marinating or soaking

    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
    “
    0.46
    ---
    0.45
    all
    0.45
    ρίζ
    0.42
    ↵
    0.42
    vie
    0.42
    ame
    0.42
    ffer
    0.42
    cout
    0.42
    He
    0.41
    POSITIVE LOGITS
     probabilmente
    0.69
     EBIT
    0.65
     showAlert
    0.64
     дов
    0.64
    绁
    0.64
    錤
    0.64
     campa
    0.63
    赜
    0.63
    茈
    0.62
     optimizations
    0.62
    Activations Density 0.003%

    No Known Activations