© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9791
    Prev
    Next
    INDEX
    Explanations

    numbers embedded in text

    oai_token-act-pair · gemini-2.0-flash

    Identifiers or version numbers

    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
    1
    -1.83
     one
    -0.99
     ১
    -0.92
    １
    -0.92
     één
    -0.83
    ১
    -0.78
     १
    -0.78
     satu
    -0.75
     jednego
    -0.70
     Один
    -0.69
    POSITIVE LOGITS
    GEBURTSDATUM
    0.78
    webElementXpaths
    0.77
    InjectAttribute
    0.69
    RenderAtEndOf
    0.69
     AssemblyCulture
    0.67
    mergeFrom
    0.64
     الحره
    0.62
    ThemeOverlay
    0.61
    MemoryWarning
    0.60
     ۸
    0.60
    Activations Density 5.529%

    No Known Activations