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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3707
    Prev
    Next
    INDEX
    Explanations

    words that are common in casual conversation and IRC, seemingly in French

    oai_token-act-pair · gemini-2.0-flash

    French/technical conversations

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     leçon
    -0.76
     charité
    -0.69
     démocratie
    -0.66
     dignité
    -0.65
     grève
    -0.65
     vallée
    -0.62
     gloire
    -0.62
     conquête
    -0.60
     prière
    -0.60
     défaite
    -0.60
    POSITIVE LOGITS
    providedIn
    0.66
    GOTREF
    0.58
    rrggbb
    0.57
    ChildScrollView
    0.57
     interaction
    0.55
    PageRoute
    0.55
    SourceChecksum
    0.54
     reflection
    0.52
    makeText
    0.52
    ollectionView
    0.52
    Activations Density 0.430%

    No Known Activations