© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13067
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and equations

    oai_token-act-pair · gemini-2.0-flash

    brackets/delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RegressionTest
    -0.55
     кор
    -0.45
    uttered
    -0.43
    bbe
    -0.41
    illère
    -0.40
     बि
    -0.40
     Pública
    -0.39
    uttering
    -0.38
    kusi
    -0.38
    UTES
    -0.37
    POSITIVE LOGITS
     '\\;'
    0.84
     Exactos
    0.80
    makeText
    0.75
     otomatig
    0.75
     ویکی‌پدیای
    0.74
    sizeCache
    0.73
     WebDriverWait
    0.72
    awtextra
    0.71
     فريبيس
    0.70
    InjectAttribute
    0.69
    Activations Density 0.693%

    No Known Activations