© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2086
    Prev
    Next
    INDEX
    Explanations

    French text with a conversational tone and common words, especially related to computer use and troubleshooting

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    п
    -0.37
    в
    -0.36
    ма
    -0.34
    о
    -0.34
    к
    -0.32
    с
    -0.32
    É
    -0.30
    же
    -0.30
    е
    -0.29
    г
    -0.29
    POSITIVE LOGITS
     avoient
    1.43
     étoient
    1.43
     ainfi
    1.34
     nôtre
    1.34
     réfrig
    1.34
     auroit
    1.28
     hâte
    1.27
     enfans
    1.27
     feroit
    1.24
     démocr
    1.23
    Activations Density 2.156%

    No Known Activations