© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3765
    Prev
    Next
    INDEX
    Explanations

    a mixture of Spanish words related to logic, the English word "besides", words related to food and desires, and the phrase "it's"

    oai_token-act-pair · gemini-2.0-flash

    Spanish language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    zzleHttp
    -0.73
    awtextra
    -0.62
    parsedMessage
    -0.61
     ProtoMessage
    -0.60
    ImageContext
    -0.59
     виправивши
    -0.58
    ScopeManager
    -0.58
     '\\;'
    -0.57
    AutoresizingMask
    -0.55
     فريبيس
    -0.55
    POSITIVE LOGITS
    äinen
    0.73
     aérienne
    0.53
     saurait
    0.52
     cherished
    0.51
     CURIAM
    0.50
    liques
    0.50
    adpleegd
    0.48
    둘
    0.48
    Gweler
    0.48
    Portail
    0.47
    Activations Density 1.960%

    No Known Activations