© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11289
    Prev
    Next
    INDEX
    Explanations

    words or punctuation that end sentences and clauses when describing television sets

    oai_token-act-pair · 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
    rungsseite
    -0.74
    lccn
    -0.61
     gyhoeddwyd
    -0.61
     estekak
    -0.59
     StatefulWidget
    -0.58
    GEBURTSDATUM
    -0.54
    Хьажоргаш
    -0.54
     ExecuteAsync
    -0.51
     OMITBAD
    -0.50
    MigrationBuilder
    -0.49
    POSITIVE LOGITS
     where
    0.73
     Where
    0.65
     WHERE
    0.60
    ginine
    0.55
     the
    0.54
     Their
    0.54
     Fans
    0.53
     dimana
    0.53
     Ideal
    0.52
    richTextPanel
    0.52
    Activations Density 0.984%

    No Known Activations