© 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. 5743
    Prev
    Next
    INDEX
    Explanations

    dates and ordinals

    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
    ँग्रेस
    2.77
     રીતે
    2.73
    र
    2.72
     useNewUrlParser
    2.70
     irresistible
    2.69
    ни
    2.66
     twinkling
    2.62
    що
    2.60
    ل
    2.55
    GREES
    2.55
    POSITIVE LOGITS
    o
    3.65
    та
    3.41
    dus
    2.91
    ে
    2.87
    д
    2.63
    ಾ
    2.62
    ے
    2.41
    resto
    2.41
     faut
    2.36
    чис
    2.35
    Activations Density 0.027%

    No Known Activations