© 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. 4156
    Prev
    Next
    INDEX
    Explanations

    russian language words and code snippets

    oai_token-act-pair · gemini-2.0-flash
    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
     تضيفلها
    -0.71
    rawDesc
    -0.71
     AssemblyCulture
    -0.70
    webElementXpaths
    -0.69
    verwijspagina
    -0.68
    Datuak
    -0.67
    Rhestr
    -0.66
     Италијани
    -0.63
    jgl
    -0.61
    piram
    -0.61
    POSITIVE LOGITS
     ele
    0.41
     poivre
    0.39
     שוליים
    0.39
    Commentaires
    0.38
     trinh
    0.36
    jsonp
    0.36
    Особенности
    0.34
    awtextra
    0.34
     truthfully
    0.34
    KeyValue
    0.34
    Activations Density 0.204%

    No Known Activations