© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3056
    Prev
    Next
    INDEX
    Explanations

    not easily measured or handled

    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_5_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
     incarnations
    0.93
     partic
    0.87
    जफ्
    0.87
    itio
    0.87
     unui
    0.86
    fty
    0.85
    ۥ
    0.85
    gever
    0.84
    effic
    0.84
    ureux
    0.84
    POSITIVE LOGITS
    वर
    1.01
    Enumerable
    0.93
    기
    0.89
    ал
    0.88
     Miscellaneous
    0.86
    Coal
    0.85
    지
    0.83
    ından
    0.82
    決
    0.82
     gutter
    0.81
    Activations Density 0.003%

    No Known Activations