© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10309
    Prev
    Next
    INDEX
    Explanations

    words, numbers, and abbreviations associated with lab experiments

    oai_token-act-pair · gemini-2.0-flash

    terms related to measurements or units

    np_token-act-pair-logits · gpt-4o-mini

    units of measurement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    contentLoaded
    -0.92
    titleMargin
    -0.77
    ViewImports
    -0.74
    AsUp
    -0.73
     GenerationType
    -0.69
    AndEndTag
    -0.66
     propOrder
    -0.65
    InjectAttribute
    -0.62
    ViewById
    -0.61
    DrawerToggle
    -0.61
    POSITIVE LOGITS
     units
    1.08
    Units
    0.96
     Units
    0.94
     unit
    0.92
    units
    0.90
    Unit
    0.89
     unidades
    0.88
     Unit
    0.86
     Einheiten
    0.79
     unità
    0.79
    Activations Density 3.996%

    No Known Activations