© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11993
    Prev
    Next
    INDEX
    Explanations

    code and filetypes like JSON

    oai_token-act-pair · gemini-2.0-flash

    json

    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
    json
    -1.83
     json
    -1.74
     JSON
    -1.55
    JSON
    -1.54
    Json
    -1.44
     Json
    -1.16
    xml
    -0.86
    yaml
    -0.82
    <bos>
    -0.77
     xml
    -0.76
    POSITIVE LOGITS
     /\.(
    0.56
    plotly
    0.51
     Rosetta
    0.49
     JpaRepository
    0.48
     Oblig
    0.47
    agung
    0.47
     Lect
    0.46
     phosphory
    0.46
     Ejército
    0.45
     pcx
    0.45
    Activations Density 7.606%

    No Known Activations