© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14615
    Prev
    Next
    INDEX
    Explanations

    place names, especially in Germany and France

    oai_token-act-pair · gemini-2.0-flash

    European locations/scientific instruments

    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
    IVEREF
    -0.69
    amını
    -0.55
    kömm
    -0.53
    లాలు
    -0.52
    ALIAN
    -0.52
    ruecos
    -0.51
     feveral
    -0.49
    wiſe
    -0.49
    elfare
    -0.49
    didSet
    -0.49
    POSITIVE LOGITS
     ***!
    0.68
    addContainerGap
    0.63
     للاسماء
    0.62
     للمعارف
    0.57
     onCreateView
    0.57
     gynhyrchwyd
    0.56
    RunWith
    0.53
    createConnection
    0.53
    UseVisualStyle
    0.52
    sizeCache
    0.52
    Activations Density 0.300%

    No Known Activations