© 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. 9738
    Prev
    Next
    INDEX
    Explanations

    substrings containing publication information, especially the New York Times, page numbers, and dates

    oai_token-act-pair · gemini-2.0-flash

    academic papers

    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
     BorderSide
    -0.47
    Personensuche
    -0.44
     turrets
    -0.40
     nozzles
    -0.40
     beams
    -0.38
     filaments
    -0.38
     Piston
    -0.38
     flies
    -0.37
     crabs
    -0.37
     Beams
    -0.37
    POSITIVE LOGITS
     EconPapers
    0.62
    SequentialGroup
    0.62
    Биография
    0.60
     Silverman
    0.58
     Social
    0.58
     Affiliations
    0.57
     Educational
    0.56
     Educators
    0.56
     Philosophy
    0.56
     Psychology
    0.56
    Activations Density 39.934%

    No Known Activations