© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10544
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies that mention traditional and modern methods

    oai_token-act-pair · gemini-2.0-flash

    traditional

    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
     traditional
    -2.20
    Traditional
    -2.11
     Traditional
    -2.05
    traditional
    -2.02
     tradi
    -1.70
    传统
    -1.65
     traditionellen
    -1.64
     тради
    -1.62
     traditionelle
    -1.61
     tradicional
    -1.52
    POSITIVE LOGITS
     BorderSide
    0.60
    GeneratedCode
    0.58
    InputBorder
    0.58
     MainAxisSize
    0.57
    RectangleBorder
    0.56
    +:+
    0.56
     aveug
    0.54
     étrangères
    0.54
    ativement
    0.53
     moeda
    0.52
    Activations Density 9.469%

    No Known Activations