© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13508
    Prev
    Next
    INDEX
    Explanations

    medical texts concerning diabetes, insulin infusion, and related treatments and conditions.

    oai_token-act-pair · gemini-2.0-flash

    medical, diabetes

    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
    DataPropertyName
    -0.50
    回戦
    -0.50
     Pro
    -0.49
     Drucker
    -0.49
    ActionPerformed
    -0.48
    Repe
    -0.47
    portál
    -0.47
    div
    -0.47
    lioma
    -0.46
    NavController
    -0.46
    POSITIVE LOGITS
    Gweler
    0.61
    ódó
    0.58
     sarili
    0.57
    monium
    0.56
     للاسماء
    0.55
     culturelles
    0.53
     vogli
    0.49
     Efq
    0.48
    ábbi
    0.48
     Monfieur
    0.47
    Activations Density 2.226%

    No Known Activations