© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10899
    Prev
    Next
    INDEX
    Explanations

    location names, specifically cities and regions.

    oai_token-act-pair · gemini-2.0-flash

    Cities and regions

    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
    الإنجليزية
    -0.86
     referenties
    -0.82
    awtextra
    -0.81
     kasarigan
    -0.81
    DockStyle
    -0.73
     AssemblyProduct
    -0.72
     متعلقه
    -0.71
    RenderAtEndOf
    -0.69
    BeginContext
    -0.69
     resourceCulture
    -0.68
    POSITIVE LOGITS
     Chicago
    1.28
     Toronto
    1.27
     Boston
    1.22
     Philadelphia
    1.17
     London
    1.16
     Atlanta
    1.14
     Montreal
    1.13
     Melbourne
    1.13
     Sydney
    1.11
     Houston
    1.11
    Activations Density 2.181%

    No Known Activations