© 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. 5395
    Prev
    Next
    INDEX
    Explanations

    dare to + verb

    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
    ट
    2.82
    uleiro
    2.79
    er
    2.54
    тың
    2.49
    elő
    2.48
    ر
    2.46
    ت
    2.43
    สัย
    2.42
    fontSize
    2.42
    ení
    2.35
    POSITIVE LOGITS
    Мы
    2.95
    ן
    2.77
    й
    2.73
     flere
    2.68
     личности
    2.65
     pembahasan
    2.49
    rowData
    2.46
    piano
    2.42
     revenir
    2.41
    ◍
    2.40
    Activations Density 0.013%

    No Known Activations