© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5746
    Prev
    Next
    INDEX
    Explanations

    content discussing Native American history and culture

    oai_token-act-pair · gemini-2.0-flash

    Native/indigenous people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    TypedDataSet
    -0.43
     createSprite
    -0.41
    uff
    -0.41
     Portuguesa
    -0.39
     ApiException
    -0.38
    globalData
    -0.38
     agre
    -0.38
    sendRedirect
    -0.37
     KeyError
    -0.37
    StringValue
    -0.36
    POSITIVE LOGITS
     Native
    1.77
     indigenous
    1.64
    Native
    1.56
     native
    1.56
    native
    1.47
     natives
    1.41
     Indigenous
    1.40
     Natives
    1.37
    Indigenous
    1.34
     tribal
    1.29
    Activations Density 4.516%

    No Known Activations