© 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. 16209
    Prev
    Next
    INDEX
    Explanations

    references to countries, states, or regions

    oai_token-act-pair · gemini-2.0-flash

    places

    np_max-act-logits · gemini-2.0-flash

    say "places"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     US
    -1.91
     American
    -1.84
    American
    -1.75
     USA
    -1.73
    US
    -1.72
     Americans
    -1.68
     american
    -1.64
     AMERICAN
    -1.61
    USA
    -1.59
    american
    -1.55
    POSITIVE LOGITS
    eleste
    0.56
    ExtendWith
    0.56
    kale
    0.56
    arakhand
    0.51
     Estonia
    0.48
     Europe
    0.48
    AutoScale
    0.47
    MigrationBuilder
    0.47
    OPSIS
    0.46
     EUROPE
    0.46
    Activations Density 7.552%

    No Known Activations