© 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. 15365
    Prev
    Next
    INDEX
    Explanations

    the phrase "search engine" or related terms.

    oai_token-act-pair · gemini-2.0-flash

    terms related to search engines

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

    search

    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
     search
    -0.91
    search
    -0.84
     searching
    -0.83
    Search
    -0.81
     searched
    -0.79
     SEARCH
    -0.77
     Search
    -0.77
    earch
    -0.76
     searches
    -0.73
     Searching
    -0.73
    POSITIVE LOGITS
     Италијани
    0.71
     незавершена
    0.67
    RRect
    0.65
    ьаж
    0.55
     Audiodateien
    0.54
     متحده
    0.53
     urma
    0.52
    addContainerGap
    0.51
    PhysRevD
    0.51
     kasarigan
    0.50
    Activations Density 2.140%

    No Known Activations