© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15770
    Prev
    Next
    INDEX
    Explanations

    non-English text especially Spanish and Portuguese newspaper titles like "La Revista Fray" or number strings with uncommon separators.

    oai_token-act-pair · gemini-2.0-flash

    A

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    styleType
    -0.73
     Paglinawan
    -0.65
    ArgumentParser
    -0.63
    ագրություններ
    -0.62
    protoimpl
    -0.62
    Espèce
    -0.56
    parsedMessage
    -0.55
    InputBorder
    -0.54
     fine
    -0.50
    Hentet
    -0.50
    POSITIVE LOGITS
    uate
    0.54
     Defects
    0.53
    msford
    0.53
     científicas
    0.53
     financière
    0.53
     cref
    0.52
     investissements
    0.52
     compito
    0.51
     proposons
    0.51
     librement
    0.51
    Activations Density 0.693%

    No Known Activations