© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14566
    Prev
    Next
    INDEX
    Explanations

    this neuron seems to activate on numbers

    oai_token-act-pair · gemini-2.0-flash

    numerical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     esternos
    -0.67
    rrggbb
    -0.67
    istoitu
    -0.67
     виправивши
    -0.66
    Архівовано
    -0.65
     ویکی‌پدیای
    -0.65
     دیکھیے
    -0.62
     transfieras
    -0.61
     Мексичка
    -0.60
    Ծանոթ
    -0.60
    POSITIVE LOGITS
    MathML
    0.66
    はじめに
    0.52
    FFF
    0.52
    BufferException
    0.49
    trä
    0.45
    GW
    0.44
    וח
    0.44
    B
    0.43
    Y
    0.42
    MW
    0.42
    Activations Density 2.324%

    No Known Activations