© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13912
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with studies and interventions.

    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_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    -1.05
    involved
    -0.98
     engage
    -0.96
     engagement
    -0.95
     involvement
    -0.94
     involved
    -0.93
    engaged
    -0.92
     engages
    -0.91
     Engaged
    -0.89
     engag
    -0.87
    POSITIVE LOGITS
    TypedDataSet
    0.77
    PerformLayout
    0.66
    parsedMessage
    0.66
     Normdatei
    0.63
    adaptiveStyles
    0.61
     الدولى
    0.60
     surla
    0.58
    DockStyle
    0.58
    ----</
    0.57
    jsxFileName
    0.56
    Activations Density 45.523%

    No Known Activations