© 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. 5590
    Prev
    Next
    INDEX
    Explanations

    shadow

    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
     facendo
    2.68
    in
    2.61
    ển
    2.59
    ן
    2.55
     sona
    2.42
     shrinkage
    2.41
    hões
    2.39
     disagree
    2.32
     Tutti
    2.30
     helplessness
    2.30
    POSITIVE LOGITS
    rijke
    2.75
    म
    2.74
    tım
    2.72
    купки
    2.48
    тана
    2.46
    
    2.40
    
    2.33
    ंकित
    2.32
    짙
    2.29
    miR
    2.29
    Activations Density 0.053%

    No Known Activations