© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13225
    Prev
    Next
    INDEX
    Explanations

    speech attribution consisting of a person's name and title followed by the word "said"

    oai_token-act-pair · gemini-2.0-flash

    quotations attributed to individuals

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

    News article quotes

    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
     Reden
    -0.50
     summary
    -0.47
    gar
    -0.46
     createState
    -0.46
    tift
    -0.45
    Statement
    -0.45
    عى
    -0.45
    lein
    -0.44
     Statement
    -0.44
     Acknowledgments
    -0.44
    POSITIVE LOGITS
     الحره
    0.82
     realising
    0.75
    ValueStyle
    0.75
    Tikang
    0.73
     privatisation
    0.68
     anaemia
    0.66
     utilising
    0.66
     realises
    0.64
    SequentialGroup
    0.64
     kasarigan
    0.63
    Activations Density 1.019%

    No Known Activations