© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3988
    Prev
    Next
    INDEX
    Explanations

    the word "tag" and related words in the context of a computer system

    oai_token-act-pair · gemini-2.0-flash

    tag

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     ostavi
    -0.85
     AssemblyTitle
    -0.81
    modelBuilder
    -0.77
    InjectAttribute
    -0.75
     AspNetCore
    -0.69
    Демографія
    -0.69
    TagMode
    -0.67
     الحره
    -0.67
    PMailer
    -0.66
    parsedMessage
    -0.66
    POSITIVE LOGITS
     걸
    0.56
    groups
    0.49
     groups
    0.47
     group
    0.47
     kelompok
    0.43
     communautés
    0.43
     sezione
    0.42
     çıkar
    0.42
    group
    0.42
    NamedQuery
    0.41
    Activations Density 1.448%

    No Known Activations