© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 43
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
     tahap
    3.31
     combustion
    3.12
    情况下
    3.08
    <bos>
    2.89
    ्सा
    2.75
    வே
    2.71
    ف
    2.71
     topped
    2.66
     ninguna
    2.63
    ブレーキ
    2.62
    POSITIVE LOGITS
     dane
    2.70
    نا
    2.57
    おります
    2.47
    োহ
    2.46
    ﺗ
    2.43
    таж
    2.42
    ңы
    2.39
    erol
    2.37
     যাইহোক
    2.34
    BackColor
    2.30
    Activations Density 0.064%

    No Known Activations