© 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. 10610
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with scientific research or academic publications

    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
    UnusedPrivate
    -0.58
    tagext
    -0.52
     predecessor
    -0.50
    internalType
    -0.50
     Goed
    -0.49
    bkz
    -0.48
     smör
    -0.46
    Igles
    -0.43
    zul
    -0.42
    ⋱
    -0.42
    POSITIVE LOGITS
     تضيفلها
    0.79
     AssemblyCompany
    0.73
     كومونز
    0.60
    seamnă
    0.57
    Cyfeiriadau
    0.57
    BeginInit
    0.57
    forChild
    0.57
     referenties
    0.57
    IGraphics
    0.56
    CompilerServices
    0.56
    Activations Density 11.170%

    No Known Activations