© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4157
    Prev
    Next
    INDEX
    Explanations

    instances of the French article "Le"

    oai_token-act-pair · gemini-2.0-flash

    Le

    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
    WebElementEntity
    -0.69
    bootstrapcdn
    -0.61
    subpackage
    -0.61
     transfieras
    -0.59
    ItemLayout
    -0.59
    SourceChecksum
    -0.56
    crystal
    -0.55
    alyptus
    -0.55
     sessionFactory
    -0.55
     Lowe
    -0.53
    POSITIVE LOGITS
    ]")]
    0.59
    hdessä
    0.57
     Plateau
    0.41
    よろしくお願いします
    0.40
    Enllaces
    0.40
    ագրություններ
    0.40
     enää
    0.39
     censiti
    0.39
    /*---
    0.38
     useRouter
    0.37
    Activations Density 0.288%

    No Known Activations