© 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. 4044
    Prev
    Next
    INDEX
    Explanations

    french words, likely in the context of casual conversation

    oai_token-act-pair · gemini-2.0-flash

    French language

    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
     nakalista
    -0.56
    endregion
    -0.55
    Revenir
    -0.54
    XmlAccessType
    -0.48
     Labor
    -0.48
    ubri
    -0.48
    ardown
    -0.47
    serviceWorker
    -0.46
    owm
    -0.44
     ContentValues
    -0.44
    POSITIVE LOGITS
     contigo
    0.65
     fallu
    0.61
     '\\;'
    0.56
     kasarigan
    0.56
     pozor
    0.55
    ardez
    0.55
    Lähteet
    0.54
     Offisielt
    0.54
     AppModule
    0.52
     électroniques
    0.52
    Activations Density 0.191%

    No Known Activations