© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13452
    Prev
    Next
    INDEX
    Explanations

    instances of people being contacted regarding some matter

    oai_token-act-pair · gemini-2.0-flash

    about / asking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    setVerticalGroup
    -0.81
    SourceChecksum
    -0.79
     jScrollPane
    -0.72
    الإنجليزية
    -0.63
     OFDb
    -0.57
    ItemBackground
    -0.55
    MethodType
    -0.54
    IUrlHelper
    -0.52
    ScopeManager
    -0.51
    RuleContext
    -0.51
    POSITIVE LOGITS
     about
    0.94
    about
    0.86
    About
    0.85
     About
    0.79
    Acerca
    0.75
     Asked
    0.72
     ABOUT
    0.70
     asking
    0.69
     tentang
    0.69
    Asking
    0.68
    Activations Density 1.570%

    No Known Activations