© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9677
    Prev
    Next
    INDEX
    Explanations

    medical vocabulary related to heart and vascular treatment involving catheters.

    oai_token-act-pair · gemini-2.0-flash

    Medical and surgical procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     שוליים
    -0.68
    expandindo
    -0.63
    principalColumn
    -0.62
    immune
    -0.54
    czyny
    -0.52
    //
    -0.52
     McCar
    -0.52
     graça
    -0.50
    writeFieldEnd
    -0.50
    paravant
    -0.50
    POSITIVE LOGITS
    AddTagHelper
    0.77
    HasBeenSet
    0.65
    djangoproject
    0.54
     drill
    0.52
     Theſe
    0.50
    stub
    0.49
    ίδι
    0.49
    drill
    0.48
    RoutingModule
    0.48
     Formations
    0.48
    Activations Density 1.463%

    No Known Activations