© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14846
    Prev
    Next
    INDEX
    Explanations

    references to scientific findings, including time, measurements, and injections

    oai_token-act-pair · gemini-2.0-flash

    research terminology

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

    say "post" or "after"

    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
    mybatisplus
    -0.91
     tramonto
    -0.86
    
    -0.83
    enderror
    -0.75
    adaptiveStyles
    -0.71
    mphony
    -0.69
     pinulongan
    -0.69
    RegressionTest
    -0.69
     ffilmiau
    -0.67
    fillType
    -0.67
    POSITIVE LOGITS
     colspan
    0.45
     study
    0.45
    beca
    0.43
    pfen
    0.42
     MEAN
    0.42
     mata
    0.42
     mean
    0.41
     Mora
    0.41
    IVAS
    0.41
     Moser
    0.40
    Activations Density 2.578%

    No Known Activations