© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16099
    Prev
    Next
    INDEX
    Explanations

    non-english words in a code or reference context

    oai_token-act-pair · gemini-2.0-flash

    mixed languages and coding

    np_max-act-logits · gemini-2.0-flash
    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
    SequentialGroup
    -0.60
     BoxDecoration
    -0.59
    ViewImports
    -0.57
     propOrder
    -0.57
     autorytatywna
    -0.56
    verwijspagina
    -0.56
     EconPapers
    -0.55
     viewDidLoad
    -0.55
    forRoot
    -0.54
     ExecuteAsync
    -0.54
    POSITIVE LOGITS
     Perſ
    0.73
     Inſ
    0.72
     ſeveral
    0.69
     Theſe
    0.67
     Beſ
    0.67
     whoſe
    0.65
     Majefty
    0.62
     Diſ
    0.62
     ſame
    0.60
     neceſſ
    0.60
    Activations Density 0.563%

    No Known Activations