© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13315
    Prev
    Next
    INDEX
    Explanations

    numbers in various formats, often related to amounts or statistics.

    oai_token-act-pair · gemini-2.0-flash

    Large numbers

    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
     thousands
    -1.95
     Thousands
    -1.80
    Thousands
    -1.73
     millions
    -1.68
    thousands
    -1.61
     Millions
    -1.55
     thousand
    -1.50
     billions
    -1.45
    Millions
    -1.41
     lakhs
    -1.40
    POSITIVE LOGITS
     pinulongan
    0.75
    complexType
    0.71
    XDECREF
    0.67
    msgTypes
    0.66
    Хьажоргаш
    0.62
     kaarangay
    0.62
     disponibilités
    0.59
    colgroup
    0.58
    IVEREF
    0.58
    jsonwebtoken
    0.58
    Activations Density 2.141%

    No Known Activations