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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2186
    Prev
    Next
    INDEX
    Explanations

    instances of mathematical denotation, where something is labeled or referred to

    oai_token-act-pair · gemini-2.0-flash

    denote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Montague
    -0.49
    <eos>
    -0.48
    ↵↵
    -0.47
     proced
    -0.46
     squadra
    -0.45
     vicenda
    -0.44
     leggera
    -0.44
    Javadoc
    -0.43
    createStatement
    -0.43
    öss
    -0.43
    POSITIVE LOGITS
    <bos>
    1.39
     autorytatywna
    0.97
    awtextra
    0.86
    QMetaType
    0.81
     الحره
    0.78
     kasarigan
    0.76
    httphttps
    0.74
    WriteTagHelper
    0.72
    RegressionTest
    0.68
    ſelves
    0.66
    Activations Density 0.371%

    No Known Activations