© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5334
    Prev
    Next
    INDEX
    Explanations

    throwing exceptions

    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
    ро
    0.92
     уважа
    0.81
    isEqualTo
    0.74
    
    0.73
     beating
    0.73
    )&=
    0.73
    maßen
    0.72
    ሁሉም
    0.72
     bril
    0.72
    ení
    0.71
    POSITIVE LOGITS
    ق
    0.90
    y
    0.83
     japonicus
    0.77
     verts
    0.76
    বুব
    0.76
    ા
    0.71
     suspected
    0.69
    াণ
    0.69
     BigDecimal
    0.69
    雩
    0.69
    Activations Density 0.002%

    No Known Activations