© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14648
    Prev
    Next
    INDEX
    Explanations

    Russian words in programming contexts

    oai_token-act-pair · gemini-2.0-flash

    technical terms or functions related to coding or data processing

    np_token-act-pair-logits · gpt-4o-mini

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     would
    -0.56
     Would
    -0.49
    Would
    -0.49
     fazia
    -0.47
    would
    -0.46
     geli
    -0.44
    Referencies
    -0.44
    ivano
    -0.44
    می
    -0.43
    дря
    -0.40
    POSITIVE LOGITS
    RegressionTest
    1.05
     EconPapers
    0.85
    WriteAttribute
    0.76
    Hentet
    0.75
     autorytatywna
    0.75
    BeginContext
    0.75
    PMailer
    0.68
    ArrowToggle
    0.67
    رشف
    0.66
    GeoNames
    0.66
    Activations Density 0.141%

    No Known Activations