© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2951
    Prev
    Next
    INDEX
    Explanations

    locations, especially in New York

    oai_token-act-pair · gemini-2.0-flash

    New York City locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     NYC
    -0.82
    NYC
    -0.81
     NY
    -0.80
     Brooklyn
    -0.78
     Manhattan
    -0.75
     Bronx
    -0.75
    NY
    -0.73
     Harlem
    -0.70
    Brooklyn
    -0.67
    nyc
    -0.65
    POSITIVE LOGITS
     resourceCulture
    0.74
     poupée
    0.65
    principalColumn
    0.65
    setVerticalGroup
    0.61
    ChildScrollView
    0.58
     cathédrale
    0.58
     Chhattisgarh
    0.56
     onBind
    0.54
     fernández
    0.54
    ⓧ
    0.54
    Activations Density 0.336%

    No Known Activations