© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12682
    Prev
    Next
    INDEX
    Explanations

    mentions of challenges, statistics, and research papers.

    oai_token-act-pair · gemini-2.0-flash

    challenges, statistics, reviews

    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
    IContainer
    -0.68
    knapp
    -0.61
    keyColumn
    -0.59
    parsedMessage
    -0.58
    contentLoaded
    -0.56
    oredCriteria
    -0.55
    Seni
    -0.54
    tiful
    -0.52
    Cursors
    -0.51
    IUrlHelper
    -0.50
    POSITIVE LOGITS
    RectangleBorder
    0.66
     numberOfRows
    0.60
    SuppressLint
    0.56
    __(/*!
    0.55
    openzeppelin
    0.51
    conten
    0.48
    abit
    0.47
    iniums
    0.46
     démocratie
    0.44
    WaitGroup
    0.43
    Activations Density 0.709%

    No Known Activations