© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3850
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something will continue to exist or a reference to a person who provided assistance.

    oai_token-act-pair · gemini-2.0-flash

    stay

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    expandindo
    -0.61
    Diweddarwch
    -0.52
    +#+
    -0.48
     DEMAND
    -0.48
    VersionUID
    -0.47
    imų
    -0.47
    Ligações
    -0.45
    BagConstraints
    -0.45
    brada
    -0.44
     Wikimedijinoj
    -0.44
    POSITIVE LOGITS
     stay
    1.97
     staying
    1.91
     stayed
    1.88
    stay
    1.84
     Stay
    1.76
     stays
    1.67
    Stay
    1.66
     STAY
    1.65
     Staying
    1.62
    Staying
    1.51
    Activations Density 0.884%

    No Known Activations