© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9576
    Prev
    Next
    INDEX
    Explanations

    code snippets related to threads

    oai_token-act-pair · gemini-2.0-flash

    Thread

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    WaitGroup
    -0.50
     thread
    -0.49
    ViewFeatures
    -0.48
    THREAD
    -0.48
     Thread
    -0.47
     onPostExecute
    -0.47
    Thread
    -0.46
    thread
    -0.45
     hilos
    -0.44
     AsyncTask
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.64
    stateProvider
    0.58
    transQ
    0.57
    lieder
    0.57
    ={({
    0.57
    GOTREF
    0.55
    TreeMap
    0.55
    Varint
    0.55
    urlpatterns
    0.55
    addContainerGap
    0.55
    Activations Density 13.505%

    No Known Activations