© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5784
    Prev
    Next
    INDEX
    Explanations

    René Descartes

    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_3_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
    
    2.07
    ে
    1.98
    𝐝
    1.81
    ⠊
    1.78
    nesdays
    1.75
    нент
    1.75
    𝐫
    1.71
    ᔪ
    1.69
    торой
    1.68
    ியது
    1.67
    POSITIVE LOGITS
    тта
    2.07
    т
    2.00
    ের
    1.98
    s
    1.96
    ת
    1.88
     tangential
    1.81
    langan
    1.77
     sectional
    1.75
    DHL
    1.75
    larında
    1.74
    Activations Density 0.000%

    No Known Activations