© 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. 12540
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "socket" and the abbreviation "SIZE", likely in the context of networking code or error messages

    oai_token-act-pair · gemini-2.0-flash

    socket

    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
    Socket
    -1.05
    socket
    -1.04
     socket
    -1.00
     Socket
    -0.93
     sockets
    -0.85
    sockets
    -0.73
    migrationBuilder
    -0.66
    Sockets
    -0.66
    fjspx
    -0.65
    SOCKET
    -0.64
    POSITIVE LOGITS
     '\\;'
    0.62
    κος
    0.52
     koş
    0.48
    hidupan
    0.47
    sproz
    0.46
     língua
    0.46
    zong
    0.45
     alcance
    0.44
    elle
    0.44
    findElement
    0.43
    Activations Density 1.416%

    No Known Activations