© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5151
    Prev
    Next
    INDEX
    Explanations

    words, symbols, and formatting characteristics of scientific papers

    oai_token-act-pair · gemini-2.0-flash

    Scientific and mathematical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ArrowToggle
    -0.62
    MethodManager
    -0.60
    WireFormatLite
    -0.59
    styleType
    -0.57
    sounds
    -0.56
    RectangleBorder
    -0.55
     defaultstate
    -0.55
    ierna
    -0.54
    yb
    -0.53
    PreferredItem
    -0.53
    POSITIVE LOGITS
    se
    0.95
    re
    0.82
    lo
    0.78
    st
    0.76
    la
    0.75
    de
    0.68
    te
    0.66
    lable
    0.66
    ce
    0.66
    ble
    0.66
    Activations Density 9.146%

    No Known Activations