© 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. 8758
    Prev
    Next
    INDEX
    Explanations

    medical or statistical terminology

    oai_token-act-pair · gemini-2.0-flash

    medical terms and complications

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

    medical complications

    np_max-act-logits · gemini-2.0-flash
    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
    richTextPanel
    -0.52
     correctes
    -0.49
    FOOTNOTES
    -0.48
    astă
    -0.47
    arbox
    -0.46
    ">—
    -0.46
    DrawerToggle
    -0.45
    makaian
    -0.43
    fjspx
    -0.42
    UMBIA
    -0.42
    POSITIVE LOGITS
     secondary
    0.61
     Viana
    0.61
    Datuak
    0.59
    styleType
    0.59
    Pranala
    0.58
    CreateModel
    0.57
    Controllo
    0.56
    hydr
    0.56
    Aiheesta
    0.54
     postoperative
    0.54
    Activations Density 3.913%

    No Known Activations