© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6452
    Prev
    Next
    INDEX
    Explanations

    words associated with medical research and facilities, especially hospitals

    oai_token-act-pair · gemini-2.0-flash

    terms related to healthcare and hospitals

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

    service locations

    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
    featureID
    -0.84
    脚注の使い方
    -0.72
    ParallelGroup
    -0.71
     BoxDecoration
    -0.66
     kasarigan
    -0.64
    richTextPanel
    -0.58
    তথ্যসূত্র
    -0.57
    cupa
    -0.56
    EDEFAULT
    -0.56
    XmlEnum
    -0.55
    POSITIVE LOGITS
    IsContent
    0.67
    front
    0.55
     gew
    0.54
     Signalez
    0.50
     ownership
    0.49
     gne
    0.48
     Sozial
    0.48
     front
    0.47
     Mileage
    0.47
     الحره
    0.46
    Activations Density 5.182%

    No Known Activations