© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7860
    Prev
    Next
    INDEX
    Explanations

    words that appear to be in a language other than English, possibly Slavic

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    inemann
    -0.46
    atchewan
    -0.46
    mutlich
    -0.44
    Personensuche
    -0.44
    resave
    -0.41
    
    -0.41
    rrggbb
    -0.41
    vaadin
    -0.41
    ็ม
    -0.40
     dark
    -0.40
    POSITIVE LOGITS
     Roskov
    0.72
    AddTagHelper
    0.71
     Beweis
    0.70
     linkovi
    0.65
    كويكب
    0.63
     intptr
    0.62
    XmlAccessType
    0.62
    انجليز
    0.61
     Réponses
    0.60
    WebServlet
    0.57
    Activations Density 0.923%

    No Known Activations