© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13593
    Prev
    Next
    INDEX
    Explanations

    data tables and statistical results from research publications

    oai_token-act-pair · gemini-2.0-flash

    medical/scientific data/reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    RegistryLite
    -0.83
    PreferredItem
    -0.81
    ArrowToggle
    -0.77
     MenuView
    -0.77
    oredCriteria
    -0.74
     pinulongan
    -0.73
    writeFieldEnd
    -0.73
    elemField
    -0.72
     AssemblyCompany
    -0.71
    MLLoader
    -0.69
    POSITIVE LOGITS
    ExecuteReader
    0.54
    makeConstraints
    0.53
    addPreferredGap
    0.53
    reportWebVitals
    0.49
     thành
    0.46
     into
    0.43
     Into
    0.43
    JI
    0.43
     possesso
    0.42
    oole
    0.41
    Activations Density 2.749%

    No Known Activations