© 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. 615
    Prev
    Next
    INDEX
    Explanations

    code, specifically Javascript and potentially other languages that use similar syntax

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · 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
    GEBURTSDATUM
    -0.75
    taur
    -0.62
     وتسجيلات
    -0.60
    yarnpkg
    -0.60
    apist
    -0.56
    økt
    -0.56
     calendriers
    -0.55
     EconPapers
    -0.52
    뀜
    -0.50
    TestingModule
    -0.50
    POSITIVE LOGITS
     تضيفلها
    0.66
    IContainer
    0.65
    شهاد
    0.62
    homonymie
    0.59
     insuffisamment
    0.59
    scriptcase
    0.52
    Enlaces
    0.51
    writeFieldEnd
    0.51
    tagext
    0.51
    Biographie
    0.50
    Activations Density 0.483%

    No Known Activations