© 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. 5465
    Prev
    Next
    INDEX
    Explanations

    news sources and websites

    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
     Ме
    1.04
     Ти
    0.97
    джа
    0.97
    о
    0.96
     Пре
    0.90
    िणी
    0.90
     Ста
    0.90
     По
    0.87
     координат
    0.87
    ુંદર
    0.86
    POSITIVE LOGITS
    mente
    0.81
    preis
    0.78
    ্ত
    0.76
    었는데
    0.75
    istiche
    0.74
    መሪያ
    0.72
    效
    0.72
     deras
    0.72
    Kaynak
    0.72
    oriale
    0.71
    Activations Density 0.066%

    No Known Activations