© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260895
    Prev
    Next
    INDEX
    Explanations

    number 1 followed by punctuation

    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_10_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
     устро
    0.49
    zels
    0.48
    뀝
    0.48
    ähl
    0.48
     salga
    0.46
     uitvo
    0.46
     Journalist
    0.45
     sowas
    0.45
     Jeder
    0.44
     흘
    0.44
    POSITIVE LOGITS
     (
    0.45
     trong
    0.45
    টি
    0.43
     eradicated
    0.42
     antica
    0.42
     डाउट्स
    0.42
    ্‌
    0.42
    这
    0.42
     Maggiore
    0.42
    vanja
    0.42
    Activations Density 0.002%

    No Known Activations