© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 227
    Prev
    Next
    INDEX
    Explanations

    phrases that appear to be advertisements or search queries related to purchasing drugs, especially from Canada or the UK, as well as mentions of "shoes", plus some medical words

    oai_token-act-pair · gemini-2.0-flash

    countries and items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    LabelTagHelper
    -0.68
    StoryboardSegue
    -0.67
    OGND
    -0.63
     дописавши
    -0.57
    addPreferredGap
    -0.57
    IsMutable
    -0.56
     المعيارى
    -0.56
    mapStateToProps
    -0.51
    usercontent
    -0.49
    displayquote
    -0.47
    POSITIVE LOGITS
     africain
    0.83
     latine
    0.77
     quæ
    0.76
     enfans
    0.72
     Efq
    0.71
     noires
    0.71
    endphp
    0.69
     cesse
    0.68
     étoit
    0.68
     avoient
    0.68
    Activations Density 0.366%

    No Known Activations