© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9809
    Prev
    Next
    INDEX
    Explanations

    descriptions of medical injuries

    oai_token-act-pair · gemini-2.0-flash

    medical 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    lccn
    -0.47
     старости
    -0.47
    wcs
    -0.46
     injuries
    -0.44
    Nguồn
    -0.43
    onViewCreated
    -0.43
    setOutput
    -0.43
    ]=>
    -0.42
    EOL
    -0.42
    dolu
    -0.41
    POSITIVE LOGITS
    >//
    0.60
     становника
    0.59
     Anexo
    0.59
    DoubleQuotes
    0.59
     اطلع
    0.59
    RunAsync
    0.59
    Varint
    0.57
    UIControlState
    0.56
    manship
    0.56
    setCellValue
    0.56
    Activations Density 4.778%

    No Known Activations