© 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. 13074
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear in medical documents like diagnoses, medical conditions, and medications

    oai_token-act-pair · gemini-2.0-flash

    psychiatric disorders

    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
    DoubleQuotes
    -0.81
    Datuak
    -0.57
    complexContent
    -0.56
    qrstuvwxyz
    -0.54
     lửa
    -0.53
     heren
    -0.53
    SuppressMessage
    -0.52
     reticulum
    -0.52
    wuchs
    -0.52
     Parlement
    -0.52
    POSITIVE LOGITS
     مشين
    0.83
    getColumnIndex
    0.58
     ddelweddau
    0.52
     nahilalakip
    0.51
    /**
    0.50
    phazard
    0.50
    autorest
    0.48
    timewa
    0.48
     springfox
    0.47
    moveToFirst
    0.47
    Activations Density 1.941%

    No Known Activations