© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13954
    Prev
    Next
    INDEX
    Explanations

    a variety of geographic place names in Europe related to government, studies, and tourism.

    oai_token-act-pair · gemini-2.0-flash

    Greece or statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     cherchés
    -0.66
    NameInMap
    -0.65
    LookAnd
    -0.64
    RegressionTest
    -0.63
     kaarangay
    -0.59
    Одно
    -0.59
     defaultstate
    -0.58
     Monfieur
    -0.58
    ThroughAttribute
    -0.58
    Демографія
    -0.57
    POSITIVE LOGITS
     (€
    0.69
    Portale
    0.69
    MADRID
    0.67
    hamshire
    0.62
     garda
    0.59
     €
    0.58
    niest
    0.56
    ajoz
    0.55
    taxia
    0.54
    出版年
    0.53
    Activations Density 2.857%

    No Known Activations