© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12846
    Prev
    Next
    INDEX
    Explanations

    words related to computing or software

    oai_token-act-pair · gemini-2.0-flash

    computer functions and tools

    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
    DeleteBehavior
    -0.57
     acaso
    -0.55
    isman
    -0.54
    berley
    -0.54
    togen
    -0.53
     Bulb
    -0.52
    ViewFeatures
    -0.52
    addContainerGap
    -0.52
    ICEF
    -0.52
    Encyclopædia
    -0.52
    POSITIVE LOGITS
    <bos>
    1.42
     وتسجيلات
    0.68
    RegressionTest
    0.67
    Datuak
    0.61
    ParallelGroup
    0.59
     useAppContext
    0.50
     use
    0.49
     समीक्षाओं
    0.49
    IntoConstraints
    0.47
    InstrumentedTest
    0.47
    Activations Density 5.009%

    No Known Activations