© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 664
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to conjunctivitis (pink eye), citizenship, and passing on values from parents and grandparents

    oai_token-act-pair · gemini-2.0-flash

    Contagious/infection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     alive
    -0.60
    ENTY
    -0.52
    asam
    -0.50
     Alive
    -0.47
    alive
    -0.47
     AssemblyProduct
    -0.46
     Unsc
    -0.46
    XtraReports
    -0.45
    asky
    -0.45
     Ant
    -0.45
    POSITIVE LOGITS
     contagious
    1.21
     contagio
    1.03
     infectious
    1.01
     contagion
    0.95
     contag
    0.94
     contagios
    0.89
     infecting
    0.85
     communic
    0.85
     infect
    0.84
     infec
    0.82
    Activations Density 0.906%

    No Known Activations