© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6923
    Prev
    Next
    INDEX
    Explanations

    words in French and related to French grammar and usage

    oai_token-act-pair · gemini-2.0-flash

    French and computing

    np_max-act-logits · gemini-2.0-flash

    French

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     avoient
    -1.06
     automatiques
    -1.05
     enfans
    -1.00
     étoient
    -0.99
     varandra
    -0.97
     électroniques
    -0.94
     vectorielles
    -0.94
     fermés
    -0.93
     scolaires
    -0.92
     sauvages
    -0.92
    POSITIVE LOGITS
    â
    0.43
     Sni
    0.42
     RAZ
    0.42
     RSP
    0.41
     Ruger
    0.41
     Avion
    0.41
     padd
    0.41
    <unused60>
    0.40
     MiG
    0.40
     GUR
    0.40
    Activations Density 0.400%

    No Known Activations