© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1832
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with study programs or scientific experiments that involve people

    oai_token-act-pair · gemini-2.0-flash

    engage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     engaged
    -1.99
     engagement
    -1.98
     engage
    -1.91
     engages
    -1.80
     Engage
    -1.80
     engaging
    -1.76
     engagements
    -1.70
     Engagement
    -1.70
    Engage
    -1.66
    Engagement
    -1.65
    POSITIVE LOGITS
     EconPapers
    0.75
     BoxFit
    0.71
     Bioaccumulative
    0.69
     AppModule
    0.67
    localctx
    0.66
    EndProject
    0.64
     MaterialApp
    0.63
    DockStyle
    0.63
    AnchorStyles
    0.62
     WebDriverWait
    0.61
    Activations Density 19.416%

    No Known Activations