© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15205
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to extracting or storing data, along with mentions of historical events like slavery

    oai_token-act-pair · gemini-2.0-flash

    extracting/fetching data or raids

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    WindowEvent
    -0.57
    WebServlet
    -0.50
     BorderSide
    -0.49
    StartCoroutine
    -0.48
    bove
    -0.47
    postDelayed
    -0.47
    getColumnIndex
    -0.47
    Migrations
    -0.46
    ArgumentParser
    -0.46
    printStackTrace
    -0.45
    POSITIVE LOGITS
     مشين
    0.81
     חיצוניים
    0.79
     termica
    0.78
     незавершена
    0.74
     Italijani
    0.70
     vocale
    0.69
     متعلقه
    0.69
     murale
    0.69
     المعيارى
    0.68
    ={({
    0.61
    Activations Density 0.665%

    No Known Activations