© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9316
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to online lending and finance, focusing on terms like "online lending," "cash," and "credit."

    oai_token-act-pair · gemini-2.0-flash

    lending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    addGap
    -0.61
    rungsseite
    -0.60
    addPreferredGap
    -0.58
    <bos>
    -0.57
    .~(\
    -0.56
    cetin
    -0.56
     ISNI
    -0.55
    QMetaType
    -0.54
    жба
    -0.53
     exercices
    -0.52
    POSITIVE LOGITS
    ViewFeatures
    0.68
    참고
    0.49
     capitals
    0.49
    GeneratedMessage
    0.49
    InputBorder
    0.48
     regulators
    0.48
     astral
    0.48
    seamnă
    0.47
    MethodManager
    0.47
    дарт
    0.47
    Activations Density 0.425%

    No Known Activations