© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14057
    Prev
    Next
    INDEX
    Explanations

    the word "French" and food-related words like "beef" and "hot"

    oai_token-act-pair · gemini-2.0-flash

    mentions of "French" and related terms

    np_token-act-pair-logits · gpt-4o-mini

    French

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     <<<<<<<<<<<<<<
    -0.77
    AddHtmlAttribute
    -0.69
     beginnetje
    -0.53
    MessageTagHelper
    -0.51
    __(/*!
    -0.50
     تضيفلها
    -0.50
    躇
    -0.47
    ParallelGroup
    -0.47
    ensation
    -0.47
     становника
    -0.47
    POSITIVE LOGITS
    TagMode
    0.61
     Lire
    0.56
     Lordships
    0.56
     Houſe
    0.55
    ńcu
    0.54
    WebVitals
    0.53
    DockStyle
    0.53
     estekak
    0.52
     pareil
    0.52
     Lordship
    0.50
    Activations Density 1.571%

    No Known Activations