© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6239
    Prev
    Next
    INDEX
    Explanations

    the term 'Lebesgue' in mathematical formulas and contexts

    oai_token-act-pair · gemini-2.0-flash

    esgue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    pidou
    -1.68
    ragamo
    -1.59
    dersfield
    -1.57
     Obrador
    -1.57
    himovic
    -1.55
    anyahu
    -1.54
    Zeneca
    -1.54
    phosa
    -1.53
    ulemon
    -1.52
     Normdatei
    -1.52
    POSITIVE LOGITS
    ous
    0.85
    ina
    0.71
    ine
    0.71
    sel
    0.68
    -
    0.67
    ce
    0.66
    ere
    0.66
    os
    0.66
    re
    0.66
    ish
    0.65
    Activations Density 2.295%

    No Known Activations