© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15386
    Prev
    Next
    INDEX
    Explanations

    language related to head injuries

    oai_token-act-pair · gemini-2.0-flash

    Head injuries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.63
    mybatisplus
    -0.61
     Wikispecies
    -0.61
    دانشنامهٔ
    -0.61
     <<<<<<<<<<<<<<
    -0.60
    endphp
    -0.57
    enderror
    -0.57
     contextLoads
    -0.56
     nahilalakip
    -0.55
    Amicalement
    -0.55
    POSITIVE LOGITS
     con
    0.81
    con
    0.72
     head
    0.68
     brain
    0.66
    Con
    0.65
     Head
    0.64
     concussion
    0.63
     Con
    0.62
    head
    0.60
    Head
    0.58
    Activations Density 1.487%

    No Known Activations