© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10503
    Prev
    Next
    INDEX
    Explanations

    code syntax keywords like 'export', 'import', 'var', 'type'

    oai_token-act-pair · gemini-2.0-flash

    Code import/export

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     import
    -2.45
     export
    -2.36
     Import
    -2.30
     imported
    -2.25
     importing
    -2.23
     imports
    -2.20
     Export
    -2.19
     exported
    -2.19
     exporting
    -2.16
     Foreign
    -2.11
    POSITIVE LOGITS
    transQ
    0.42
    UALA
    0.40
    node
    0.36
     getNode
    0.36
    tudo
    0.35
     gik
    0.35
     imp
    0.35
    TEMPLATES
    0.35
    FieldBuilder
    0.35
    elemField
    0.34
    Activations Density 0.943%

    No Known Activations