© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6895
    Prev
    Next
    INDEX
    Explanations

    mentions of France, especially in the context of bicycle racing

    oai_token-act-pair · gemini-2.0-flash

    France

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     France
    -1.84
     French
    -1.82
    French
    -1.63
     french
    -1.63
    France
    -1.59
     france
    -1.53
     FRENCH
    -1.51
    french
    -1.48
     Frenchman
    -1.40
     Francia
    -1.35
    POSITIVE LOGITS
     صوتيه
    0.80
     disambiguazione
    0.64
     betweenstory
    0.63
    țiilor
    0.58
     relâche
    0.58
     "..\..\..\
    0.56
    enumii
    0.54
    titleMargin
    0.54
    hical
    0.52
    олові
    0.52
    Activations Density 0.934%

    No Known Activations