© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11735
    Prev
    Next
    INDEX
    Explanations

    words related to legal and business documents

    oai_token-act-pair · gemini-2.0-flash

    say "to" post token

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     AssemblyCulture
    -0.98
    OGND
    -0.82
     kasarigan
    -0.75
    ViewFeatures
    -0.73
    ConstraintMaker
    -0.66
    IntoConstraints
    -0.62
     AssemblyVersion
    -0.62
    InputBorder
    -0.61
     AssemblyCompany
    -0.59
    WebVitals
    -0.59
    POSITIVE LOGITS
     kepada
    1.18
    tothe
    1.06
     to
    1.02
    给
    1.00
     unto
    1.00
     vnto
    0.95
    給
    0.87
     thereto
    0.83
     aos
    0.79
     给
    0.77
    Activations Density 2.457%

    No Known Activations