© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1805
    Prev
    Next
    INDEX
    Explanations

    a jumbled mix of location words with related prepositions, conjunctions, and question words

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "there."

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

    there

    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
    Negative Logits
    findpost
    -0.66
    quise
    -0.55
    EntityFramework
    -0.52
     ausz
    -0.51
    าก็
    -0.49
    setRequest
    -0.49
     lemme
    -0.48
     kiện
    -0.47
    InitVars
    -0.46
    wnież
    -0.46
    POSITIVE LOGITS
     there
    2.78
    there
    2.19
     THERE
    1.91
    There
    1.88
     There
    1.88
    THERE
    1.67
     theres
    1.38
     هناك
    1.30
    theres
    1.24
    Theres
    1.06
    Activations Density 4.283%

    No Known Activations