© 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. 14231
    Prev
    Next
    INDEX
    Explanations

    research papers and scientific studies, possibly based on the presence of bracketed citation markers and related terms

    oai_token-act-pair · gemini-2.0-flash

    foreign languages/code

    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
    WebServlet
    -0.57
    getWriter
    -0.50
    ||}
    -0.49
    didReceive
    -0.48
     تانيه
    -0.46
    вік
    -0.46
    rony
    -0.44
    atte
    -0.44
     насељу
    -0.42
    isier
    -0.42
    POSITIVE LOGITS
     للاسماء
    0.89
    :✨
    0.73
    ExecuteReader
    0.59
    IndentedString
    0.56
    发表于
    0.54
     SIMBAD
    0.54
    InjectAttribute
    0.54
     AssemblyCulture
    0.54
     profili
    0.54
     VizieR
    0.53
    Activations Density 4.779%

    No Known Activations