© 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. 15116
    Prev
    Next
    INDEX
    Explanations

    mentions of Irish rugby teams and players

    oai_token-act-pair · gemini-2.0-flash

    rugby and sports

    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
    исленность
    -0.56
     >=",
    -0.56
     المعيارى
    -0.54
    isContained
    -0.52
    raszam
    -0.51
     szóci
    -0.50
     masak
    -0.48
     Prata
    -0.48
    ISupport
    -0.47
     саны
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.58
    новниш
    0.52
    ècie
    0.52
    :✨
    0.52
    enciaga
    0.50
    Morfologia
    0.50
     Squad
    0.50
    Squad
    0.48
     виправивши
    0.48
    InstrumentedTest
    0.48
    Activations Density 1.270%

    No Known Activations