© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4373
    Prev
    Next
    INDEX
    Explanations

    words related to disease diagnoses or medical procedures

    oai_token-act-pair · gemini-2.0-flash

    medical/histological examinations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Revenir
    -0.51
    ็จ
    -0.47
    CreateModel
    -0.47
    وصف
    -0.47
    MLLoader
    -0.46
    SqlClient
    -0.45
    ########.
    -0.44
    opsida
    -0.44
     članak
    -0.44
     encoding
    -0.43
    POSITIVE LOGITS
     Wicidata
    0.60
     kaarangay
    0.57
    談社
    0.56
     autorytatywna
    0.54
    endpush
    0.54
     parseFrom
    0.54
    IBAction
    0.53
    istical
    0.53
    Datuak
    0.52
     Crusoe
    0.52
    Activations Density 5.924%

    No Known Activations