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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10219
    Prev
    Next
    INDEX
    Explanations

    a variety of words that depend on the context of the article

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    httphttps
    -0.71
     nahilalakip
    -0.66
     beginnetje
    -0.65
    setViewportView
    -0.57
     مشين
    -0.57
    parsedMessage
    -0.56
    MessageTagHelper
    -0.55
     Vikipedi
    -0.52
    UrlEncoded
    -0.52
    invokeLater
    -0.50
    POSITIVE LOGITS
    曖昧さ回避
    0.61
    是否有
    0.60
    thâu
    0.58
     protoimpl
    0.55
    ItemBackground
    0.55
    ResponseWriter
    0.55
    是不是
    0.54
     suspect
    0.54
    Vielleicht
    0.54
     whether
    0.53
    Activations Density 4.033%

    No Known Activations