© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15420
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in scientific publications, including reporting of results, descriptions of experiments, and acknowledgements

    oai_token-act-pair · gemini-2.0-flash

    Scientific conclusions/acknowledgements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Efq
    -0.96
     Diſ
    -0.90
     cref
    -0.88
     Reſ
    -0.85
     Inſ
    -0.84
     greateſt
    -0.84
     itſelf
    -0.82
     ſch
    -0.81
     iſt
    -0.81
     Jefus
    -0.81
    POSITIVE LOGITS
    <eos>
    0.54
    „
    0.51
    ↵↵
    0.51
     d
    0.50
    '
    0.50
     autorytatywna
    0.50
     „
    0.48
    不但
    0.47
     (
    0.45
    تي
    0.45
    Activations Density 4.529%

    No Known Activations