© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6728
    Prev
    Next
    INDEX
    Explanations

    medical research texts, specifically phrases relating to asthma and obesity

    oai_token-act-pair · gemini-2.0-flash

    technical terms and concepts

    np_token-act-pair-logits · gpt-4o-mini

    research 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     AttributeSet
    -0.48
     RoutedEventArgs
    -0.47
    }));
    -0.45
    ([]);
    -0.44
    iertas
    -0.44
     exh
    -0.44
     staden
    -0.43
     समीक्षक
    -0.43
     communicates
    -0.42
    次代
    -0.41
    POSITIVE LOGITS
    AndEndTag
    0.87
    SourceChecksum
    0.77
    ModelBuilder
    0.66
    +#+#
    0.66
     "..\..\..\
    0.65
    ParallelGroup
    0.62
    :✨
    0.62
    currentColor
    0.61
    بوابة
    0.60
    KommentareTeilen
    0.59
    Activations Density 2.296%

    No Known Activations