© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10754
    Prev
    Next
    INDEX
    Explanations

    words related to computer networks

    oai_token-act-pair · gemini-2.0-flash

    network

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     network
    -2.45
     Network
    -2.17
    network
    -2.16
    Network
    -2.09
     NETWORK
    -1.91
     networks
    -1.85
     Networks
    -1.75
    NETWORK
    -1.64
     réseau
    -1.59
    Networks
    -1.52
    POSITIVE LOGITS
    ThroughAttribute
    0.73
    rungsseite
    0.70
    IUrlHelper
    0.65
     CreateTagHelper
    0.64
     gyhoeddwyd
    0.59
    Personendaten
    0.59
     ModelExpression
    0.58
    ⓧ
    0.57
    AutoScale
    0.56
    )$}
    0.56
    Activations Density 0.695%

    No Known Activations