© 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. 40
    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
    ਆਂ
    0.47
    পূ
    0.45
     অপর্ণ
    0.44
    친구
    0.43
     tgt
    0.42
    
    0.42
    Мар
    0.42
     arginine
    0.41
    惊
    0.41
    siz
    0.40
    POSITIVE LOGITS
    ot
    0.64
    ers
    0.49
    xiety
    0.46
    ها
    0.44
    ance
    0.43
    body
    0.42
    ings
    0.42
    ść
    0.41
    uje
    0.40
    个小时
    0.39
    Activations Density 0.440%

    No Known Activations