© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13366
    Prev
    Next
    INDEX
    Explanations

    the French word "Le" or other words starting with those letters

    oai_token-act-pair · gemini-2.0-flash

    French references

    np_max-act-logits · gemini-2.0-flash

    Le

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    Einzelnachweise
    -0.52
    IMPORTED
    -0.48
     par
    -0.47
     [
    -0.46
     note
    -0.46
    sian
    -0.46
    ตร
    -0.46
    ква
    -0.45
     aus
    -0.45
    [
    -0.45
    POSITIVE LOGITS
     فريبيس
    0.91
    UserScript
    0.88
    Geplaatst
    0.85
    SharedDtor
    0.79
    LookAnd
    0.78
    ^(@)
    0.77
    Tikang
    0.77
    Personendaten
    0.76
     fermée
    0.75
     Италијани
    0.74
    Activations Density 1.588%

    No Known Activations