© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11350
    Prev
    Next
    INDEX
    Explanations

    mentions of "Washington, D.C." along with other locations and entities

    oai_token-act-pair · gemini-2.0-flash

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    errHandler
    -0.79
    AxisAlignment
    -0.62
     estekak
    -0.62
     comuniques
    -0.60
    dirond
    -0.60
     يتيمه
    -0.59
     SUT
    -0.58
     contextLoads
    -0.57
     Mafia
    -0.57
     Вікіпе
    -0.57
    POSITIVE LOGITS
     Canberra
    0.88
     Redskins
    0.77
    WASHINGTON
    0.75
     Washington
    0.73
     Abuja
    0.72
    Washington
    0.71
     DC
    0.69
    Abuja
    0.63
     Islamabad
    0.63
    <bos>
    0.63
    Activations Density 1.222%

    No Known Activations