© 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. 5571
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, especially countries and regions, in a formal or business context.

    oai_token-act-pair · gemini-2.0-flash

    locations and world contexts

    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
     Americans
    -1.16
     American
    -1.16
    country
    -1.13
     country
    -1.13
     Canadians
    -1.09
    American
    -1.09
     american
    -1.07
     Australians
    -1.06
    Americans
    -1.06
     America
    -1.06
    POSITIVE LOGITS
    setVerticalGroup
    0.54
    нъ
    0.51
    Spoljašnje
    0.49
     {}'.
    0.48
    rungsseite
    0.48
     liev
    0.45
    ütü
    0.44
    abin
    0.44
    cheiben
    0.44
    ayet
    0.44
    Activations Density 2.660%

    No Known Activations