© 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. 10415
    Prev
    Next
    INDEX
    Explanations

    terms related to network packets and their headers

    oai_token-act-pair · gemini-2.0-flash

    packet

    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
     >=",
    -0.61
    gelopen
    -0.56
    rrggbb
    -0.55
    éndolo
    -0.55
     satin
    -0.52
    spesies
    -0.49
     getS
    -0.48
    Shiny
    -0.48
     Sociales
    -0.47
     Huguen
    -0.47
    POSITIVE LOGITS
    MetaObject
    0.63
     Paglinawan
    0.60
    InstrumentedTest
    0.59
    asteroide
    0.58
     архивлан
    0.56
    Geplaatst
    0.55
     चीज़ों
    0.54
    JspWriter
    0.54
    ыгана
    0.53
    FieldNumber
    0.52
    Activations Density 2.772%

    No Known Activations