© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9829
    Prev
    Next
    INDEX
    Explanations

    the number 3, especially in the context of document or figure labels, and sometimes combined with other numbers like 8, 9, 10, 1 or 5

    oai_token-act-pair · gemini-2.0-flash

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    PRNewswire
    -0.51
     carbone
    -0.51
    IActionResult
    -0.50
    南浔
    -0.48
    -0.48
    inhas
    -0.47
    AppCompat
    -0.47
    PREC
    -0.46
    codegen
    -0.46
    iNdEx
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.84
    ItemBackground
    0.73
     disambiguazione
    0.71
     мәкал
    0.69
     للاسماء
    0.68
     censiti
    0.66
    SharedDtor
    0.64
    SourceChecksum
    0.63
    Suivez
    0.62
     autorytatywna
    0.62
    Activations Density 0.918%

    No Known Activations