© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3635
    Prev
    Next
    INDEX
    Explanations

    medical certificate

    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
    t
    1.86
    ু
    1.71
    traction
    1.69
    ήθ
    1.66
    ább
    1.54
     fica
    1.49
    frak
    1.49
    Britt
    1.48
    anlage
    1.48
    อร์
    1.47
    POSITIVE LOGITS
    Ре
    1.97
    ','"+
    1.90
     singled
    1.89
     осозна
    1.85
    itory
    1.79
     Обычно
    1.79
    𝐭
    1.78
    Д
    1.69
    িত্ত
    1.68
    ॉजी
    1.64
    Activations Density 0.000%

    No Known Activations