© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14253
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms, particularly in the context of medical imaging and programming

    oai_token-act-pair · gemini-2.0-flash

    medical imaging terms

    np_token-act-pair-logits · gpt-4o-mini

    CT scans

    np_max-act-logits · gemini-2.0-flash

    CT

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Tikang
    -0.66
    HtmlAttribute
    -0.64
     >=",
    -0.62
    IntoConstraints
    -0.60
     memoized
    -0.58
    createCell
    -0.57
     RISERVATA
    -0.56
    ofday
    -0.55
     createState
    -0.54
    avras
    -0.54
    POSITIVE LOGITS
     astore
    0.56
     تضيفلها
    0.54
    co
    0.52
    er
    0.51
    ers
    0.50
    tab
    0.49
     ویکی‌پدی
    0.49
    ba
    0.48
    Izvori
    0.48
    le
    0.47
    Activations Density 3.205%

    No Known Activations