© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10796
    Prev
    Next
    INDEX
    Explanations

    French words and/or internet forum/chat-like language

    oai_token-act-pair · gemini-2.0-flash

    non-english text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     lipat
    -0.57
     vocale
    -0.50
     frische
    -0.49
    gifter
    -0.47
     isolato
    -0.47
    dbl
    -0.46
     Drawer
    -0.46
     gewöhnlich
    -0.45
     ringan
    -0.45
    MigrationBuilder
    -0.45
    POSITIVE LOGITS
     utafitiHapana
    0.89
     ivelany
    0.63
    èdia
    0.63
    DoubleQuotes
    0.57
    paramMap
    0.55
    apnews
    0.54
    XMLSchema
    0.52
    glDelete
    0.51
    )__
    0.50
    WebVitals
    0.50
    Activations Density 0.951%

    No Known Activations