© 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. 7413
    Prev
    Next
    INDEX
    Explanations

    names of people and places, especially when discussing genealogy and the American Civil War

    oai_token-act-pair · gemini-2.0-flash

    Southern history/genealogy

    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
    Personensuche
    -0.71
     Minneapolis
    -0.62
    
    -0.62
     EconPapers
    -0.62
    EndGlobalSection
    -0.58
    Minneapolis
    -0.58
    Minnesota
    -0.57
     povezave
    -0.56
     Minnesota
    -0.55
    versy
    -0.55
    POSITIVE LOGITS
     виправивши
    0.56
     Tennessee
    0.55
    clerview
    0.54
     daddy
    0.53
     Alabama
    0.52
     Eub
    0.52
    ProcessEvent
    0.52
    fromCharCode
    0.52
    makeText
    0.51
     TVA
    0.51
    Activations Density 2.586%

    No Known Activations