© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13007
    Prev
    Next
    INDEX
    Explanations

    words that are used to describe something as other than average

    oai_token-act-pair · gemini-2.0-flash

    business people

    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
    RegressionTest
    -0.71
     ग्राहकों
    -0.57
    Santis
    -0.52
    TableHead
    -0.52
    angeran
    -0.52
    ViewFeatures
    -0.50
    NOSIS
    -0.49
    Audiences
    -0.49
     referenties
    -0.49
     customers
    -0.49
    POSITIVE LOGITS
     retailer
    0.83
     shops
    0.77
     businesses
    0.76
     retailers
    0.76
     craftsmen
    0.74
     merchants
    0.73
     artists
    0.72
     makers
    0.72
     builders
    0.71
     creators
    0.71
    Activations Density 1.715%

    No Known Activations