Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14070
    Prev
    Next
    INDEX
    Explanations

    medical and biological terms, especially related to the digestive and respiratory systems

    oai_token-act-pair · gemini-2.0-flash

    scientific/medical texts (intestines/saliva)

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.89
    abestanden
    -0.76
    intios
    -0.68
     utafitiHapana
    -0.66
    IntoConstraints
    -0.56
    vician
    -0.54
     Савезне
    -0.52
    SharedCtor
    -0.52
    QMetaType
    -0.51
     defaultstate
    -0.51
    POSITIVE LOGITS
     AttributeSet
    0.63
    izoen
    0.61
    pédie
    0.56
    nastics
    0.56
    oglobulin
    0.55
    dehyde
    0.54
    वाद
    0.53
    mpty
    0.52
    marginHorizontal
    0.51
    ity
    0.51
    Activations Density 3.267%

    No Known Activations