© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13588
    Prev
    Next
    INDEX
    Explanations

    articles, prepositions, and some determiners

    oai_token-act-pair · gemini-2.0-flash

    of or the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    <eos>
    -0.76
    .
    -0.69
    (
    -0.67
     [
    -0.66
     (
    -0.65
    una
    -0.64
    esa
    -0.60
    |
    -0.60
    ,
    -0.60
    aarrggbb
    -0.59
    POSITIVE LOGITS
     itſelf
    1.38
     myſelf
    1.30
    ſelves
    1.27
    ſelf
    1.25
     Jefus
    1.24
     Efq
    1.23
     ་་
    1.23
     houſe
    1.20
     Houſe
    1.19
     themſelves
    1.17
    Activations Density 11.592%

    No Known Activations