© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9362
    Prev
    Next
    INDEX
    Explanations

    differences between two versions of code, as indicated by diff output

    oai_token-act-pair · gemini-2.0-flash

    addition symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    endforeach
    -0.57
    URLException
    -0.50
     BoxFit
    -0.47
     rang
    -0.47
    +};
    -0.46
    __))
    -0.44
     MEASURE
    -0.43
     det
    -0.43
    webElementXpaths
    -0.42
    Intermediate
    -0.42
    POSITIVE LOGITS
    المشاركات
    0.66
    Източници
    0.66
    ":[{
    0.62
    KommentareTeilen
    0.61
     Efq
    0.59
     ***!
    0.55
     kaynağından
    0.54
    INDUSTRY
    0.53
    Viited
    0.51
    Бележки
    0.51
    Activations Density 6.785%

    No Known Activations