© 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. 12621
    Prev
    Next
    INDEX
    Explanations

    mentions of people and their relationships or roles

    oai_token-act-pair · gemini-2.0-flash

    people

    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
     people
    -1.20
    people
    -1.13
    People
    -1.08
     person
    -1.02
     People
    -1.00
     PEOPLE
    -0.95
    PEOPLE
    -0.93
     folks
    -0.87
     Menschen
    -0.86
    Person
    -0.85
    POSITIVE LOGITS
    parsedMessage
    0.85
    ViewImports
    0.66
    UnusedPrivate
    0.63
    WebVitals
    0.63
    apunov
    0.61
     Independiente
    0.59
     NSCoder
    0.55
     Ordovician
    0.55
    ########.
    0.54
    onViewCreated
    0.54
    Activations Density 17.470%

    No Known Activations