© 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. 5260
    Prev
    Next
    INDEX
    Explanations

    conjugation or dialectical behavior

    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
     quadrants
    2.60
    ो
    2.54
    serif
    2.41
     cof
    2.41
    लोड
    2.38
     rspace
    2.37
    DUCTION
    2.35
     önce
    2.31
     azienda
    2.31
     convocatoria
    2.30
    POSITIVE LOGITS
    ate
    2.98
     nourished
    2.73
    ال
    2.69
    વ
    2.61
    🟡
    2.55
     stvar
    2.45
    جے
    2.44
    一个
    2.43
     riten
    2.41
     рядом
    2.41
    Activations Density 0.013%

    No Known Activations