© 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. 5390
    Prev
    Next
    INDEX
    Explanations

    a variety of words written in Russian or code, as well as legal terms

    oai_token-act-pair · gemini-2.0-flash

    code, foreign language, legal documents

    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
    IndentedString
    -0.63
     sumpay
    -0.57
    parsedMessage
    -0.52
    HasForeignKey
    -0.51
     تضيفلها
    -0.50
     الحره
    -0.50
     AssemblyCompany
    -0.50
    __":
    -0.47
    Rujuakan
    -0.47
     Wikimedijinoj
    -0.47
    POSITIVE LOGITS
    SourceChecksum
    0.55
    bürgermeister
    0.52
    ieden
    0.52
    Condol
    0.51
     FontWeight
    0.51
    ấc
    0.50
     Cataloging
    0.50
    eadilan
    0.49
    ibig
    0.48
     elever
    0.48
    Activations Density 0.492%

    No Known Activations