© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11434
    Prev
    Next
    INDEX
    Explanations

    the names of regions and towns in France, especially in the context of administrative divisions

    oai_token-act-pair · gemini-2.0-flash

    France, places

    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
     "..\..\..\
    -0.79
     snippetHide
    -0.78
    rawDesc
    -0.73
     Monfieur
    -0.71
    DockStyle
    -0.67
    cloudfront
    -0.67
    ValueStyle
    -0.67
    WithIOException
    -0.66
     Efq
    -0.65
     itſelf
    -0.65
    POSITIVE LOGITS
    setupUi
    0.47
     <<<<<<<<<<<<<<
    0.45
    :✨
    0.45
    Po
    0.44
     Norman
    0.44
     Y
    0.41
    Norman
    0.41
     pas
    0.41
    FF
    0.40
    Y
    0.40
    Activations Density 0.724%

    No Known Activations