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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6798
    Prev
    Next
    INDEX
    Explanations

    mostly short words, especially articles, prepositions, and pronouns, in French.

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act · gemini-2.0-flash

    French function words

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     semi
    -0.46
     geval
    -0.46
    LVL
    -0.44
     by
    -0.44
    cplusplus
    -0.43
    ([^
    -0.43
    ragon
    -0.43
     because
    -0.43
     omdat
    -0.42
     broke
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.94
     PeEnEo
    0.80
     cherchés
    0.79
     >=",
    0.78
     viewDidLoad
    0.78
     autorytatywna
    0.76
    脚注の使い方
    0.75
    évaluateur
    0.73
     <>",
    0.72
    setof
    0.71
    Activations Density 0.268%

    No Known Activations