© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6406
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and finance, especially those involving market analysis, soil composition, and medical conditions

    oai_token-act-pair · gemini-2.0-flash

    activity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    InjectAttribute
    -0.87
    twimg
    -0.87
    parsedMessage
    -0.86
     EconPapers
    -0.85
    IsContent
    -0.84
    uxxxx
    -0.82
    
    -0.80
     NSCoder
    -0.79
    MemoryWarning
    -0.77
     propOrder
    -0.77
    POSITIVE LOGITS
     activity
    1.75
    activity
    1.53
     Activity
    1.45
    Activity
    1.45
     ACTIVITY
    1.25
     actividad
    1.19
    ACTIVITY
    1.19
     activité
    1.17
     activities
    1.09
     atividade
    1.08
    Activations Density 2.655%

    No Known Activations