© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9983
    Prev
    Next
    INDEX
    Explanations

    words and contexts related to medical treatments and conditions.

    oai_token-act-pair · gemini-2.0-flash

    Medical treatments and conditions

    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
     utafitiHapana
    -0.57
    }{*}{
    -0.52
    poz
    -0.51
    NonQuery
    -0.50
    fortawesome
    -0.50
     reserve
    -0.50
     IActionResult
    -0.49
    تقاوى
    -0.49
     Norman
    -0.49
    ☚
    -0.49
    POSITIVE LOGITS
     NSCoder
    0.60
     Theſe
    0.59
    Datuak
    0.59
     ſtate
    0.58
     faſt
    0.53
     ſche
    0.51
     houſe
    0.51
     OCC
    0.50
     StatefulWidget
    0.49
     uſed
    0.49
    Activations Density 1.585%

    No Known Activations