© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2867
    Prev
    Next
    INDEX
    Explanations

    words related to computer cluster management, especially in the context of Apache Spark and Elastic Beanstalk

    oai_token-act-pair · gemini-2.0-flash

    node

    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
    Negative Logits
     propOrder
    -0.83
     EconPapers
    -0.76
    ThroughAttribute
    -0.71
    Solución
    -0.67
    EndGlobalSection
    -0.65
    onActivityResult
    -0.65
    modelBuilder
    -0.65
     defaultstate
    -0.64
    DataAnnotations
    -0.63
    featureID
    -0.63
    POSITIVE LOGITS
     node
    0.72
     nodes
    0.70
    node
    0.59
     master
    0.59
    Node
    0.56
     worker
    0.55
     Node
    0.53
    Nodes
    0.53
     leader
    0.53
    leader
    0.53
    Activations Density 2.864%

    No Known Activations