© 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. 12742
    Prev
    Next
    INDEX
    Explanations

    scientific language related to research and/or medicine

    oai_token-act-pair · gemini-2.0-flash

    scientific research/pharmaceuticals

    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
    Share
    -0.47
    ala
    -0.46
     Teilen
    -0.45
     contribué
    -0.44
     materiál
    -0.42
     Empire
    -0.41
    kto
    -0.41
     payé
    -0.41
     henne
    -0.40
     publisher
    -0.40
    POSITIVE LOGITS
    inaison
    0.77
    TypedDataSet
    0.77
    principalColumn
    0.75
     SEDS
    0.71
    ItemBackground
    0.71
    Jeografia
    0.68
     initComponents
    0.67
     незавершена
    0.67
    CodeAttribute
    0.66
    styleType
    0.66
    Activations Density 3.722%

    No Known Activations