© 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. 2867
    Prev
    Next
    INDEX
    Explanations

    handleSubmit

    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
    즌
    0.82
    т
    0.79
    ت
    0.77
    ু
    0.72
    لل
    0.68
    MPI
    0.68
    '}
    0.67
    aler
    0.67
     commencement
    0.67
    जनन
    0.67
    POSITIVE LOGITS
    ्स
    0.71
     inversely
    0.69
    czaj
    0.69
    eep
    0.69
    ⃝
    0.68
    इट
    0.67
    ্ধ্য
    0.67
    ног
    0.67
     ای
    0.66
    icult
    0.66
    Activations Density 0.002%

    No Known Activations