© 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. 5801
    Prev
    Next
    INDEX
    Explanations

    paths, URLs, names, numbers, or positive

    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
    োপুরি
    3.34
     불구하고
    3.28
    igating
    2.95
    तक
    2.87
    োতে
    2.81
    ক
    2.77
     मिलकर
    2.71
    لنا
    2.70
     denominator
    2.68
    대학교
    2.67
    POSITIVE LOGITS
    y
    3.46
    ی
    3.37
    т
    3.04
    ت
    3.02
    س
    2.96
    즌
    2.95
     kend
    2.92
    তার
    2.80
    s
    2.80
    i
    2.78
    Activations Density 0.092%

    No Known Activations