© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13249
    Prev
    Next
    INDEX
    Explanations

    pronouns and articles in different languages seemingly at random

    oai_token-act-pair · gemini-2.0-flash

    latter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     GenerationType
    -0.84
    ApplicationTests
    -0.62
    HtmlAttribute
    -0.62
     Roskov
    -0.61
    IPAC
    -0.61
     REGISTRATION
    -0.60
     BoxFit
    -0.60
     EMPLOYEES
    -0.59
    hion
    -0.59
     adul
    -0.59
    POSITIVE LOGITS
    <bos>
    0.64
    wpi
    0.52
    DoubleQuotes
    0.49
    ádza
    0.49
    </caption>
    0.46
     které
    0.45
     nawr
    0.45
     które
    0.43
    [](
    0.42
     namelijk
    0.42
    Activations Density 1.537%

    No Known Activations