© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3128
    Prev
    Next
    INDEX
    Explanations

    code snippets involving lists, maps, and method stubs

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    Negative Logits
    AndEndTag
    -0.70
     continúas
    -0.62
    GEBURTSDATUM
    -0.60
    odata
    -0.57
    èdia
    -0.57
     ModelExpression
    -0.57
    出版年
    -0.54
    writeFieldEnd
    -0.53
    Ҭ
    -0.53
    carbonate
    -0.52
    POSITIVE LOGITS
    <bos>
    0.90
     iLocal
    0.68
    /**
    0.61
    lüğü
    0.59
    #
    0.58
     tanken
    0.56
    PriorityQueue
    0.56
    reactstrap
    0.54
    unistd
    0.54
     Allí
    0.54
    Activations Density 3.212%

    No Known Activations