© 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. 10308
    Prev
    Next
    INDEX
    Explanations

    code snippets with URLs, file paths, and/or mathematical notation

    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
    URLException
    -0.57
     Gleichzeitig
    -0.52
     FetchType
    -0.52
     År
    -0.50
    tableFuture
    -0.50
     Jeb
    -0.49
    ándor
    -0.48
     BoxFit
    -0.48
     derselbe
    -0.48
    formKey
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.83
    OGND
    0.72
     jScrollPane
    0.71
    awtextra
    0.62
    omitempty
    0.60
    UnitTesting
    0.57
    :✨
    0.56
    Personendaten
    0.55
     jLabel
    0.54
    NameInMap
    0.54
    Activations Density 4.934%

    No Known Activations