© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9726
    Prev
    Next
    INDEX
    Explanations

    text that is part of a discussion, likely in a forum, about technical topics, possibly including references to French language items

    oai_token-act-pair · gemini-2.0-flash

    French language

    np_max-act-logits · 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_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
    日閲覧
    -0.57
     du
    -0.56
     sur
    -0.55
     qu
    -0.50
    StoryboardSegue
    -0.49
     ơn
    -0.49
    siyon
    -0.49
    Activités
    -0.49
    btnBack
    -0.48
     muuta
    -0.48
    POSITIVE LOGITS
     autorytatywna
    0.63
    HomeAsUpEnabled
    0.55
    ագրություններ
    0.54
     spade
    0.49
    structors
    0.48
    AsUp
    0.47
    러나
    0.47
     "..\..\
    0.46
     poured
    0.46
    WITHOUT
    0.45
    Activations Density 0.646%

    No Known Activations