© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12921
    Prev
    Next
    INDEX
    Explanations

    descriptions of medical emergencies response

    oai_token-act-pair · gemini-2.0-flash

    injuries and accidents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     lo
    -0.50
    tance
    -0.47
    VV
    -0.46
    t
    -0.43
     up
    -0.43
    räger
    -0.43
    浮か
    -0.42
     Bailey
    -0.41
    Whereas
    -0.41
    ogh
    -0.40
    POSITIVE LOGITS
    NameInMap
    0.73
    protoc
    0.63
     reager
    0.62
    EDEFAULT
    0.62
    setVerticalGroup
    0.62
    Personendaten
    0.61
    writeFieldEnd
    0.61
     distanciation
    0.60
    ANDUM
    0.58
     ddelweddau
    0.57
    Activations Density 1.296%

    No Known Activations