© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8744
    Prev
    Next
    INDEX
    Explanations

    words related to scientific research about medicine

    oai_token-act-pair · gemini-2.0-flash

    medical trials and studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     désolés
    -0.49
    str
    -0.42
    esModule
    -0.41
     Great
    -0.37
     Alle
    -0.36
     Place
    -0.36
    ীর
    -0.36
    Great
    -0.35
    Re
    -0.35
    currentValue
    -0.35
    POSITIVE LOGITS
     EClass
    0.90
    protoimpl
    0.90
    featureID
    0.83
     disambiguazione
    0.79
     jScrollPane
    0.77
    ########.
    0.75
    onViewCreated
    0.75
     Meksiku
    0.75
    ViewFeatures
    0.73
    SourceChecksum
    0.73
    Activations Density 2.886%

    No Known Activations