© 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. 7819
    Prev
    Next
    INDEX
    Explanations

    words related to societal and political entities and formal systems

    oai_token-act-pair · gemini-2.0-flash

    International/global issues

    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
    glBegin
    -0.56
     beurre
    -0.53
    glColor
    -0.49
    SqlClient
    -0.48
     Tapatalk
    -0.47
    Források
    -0.46
    MENAFN
    -0.46
    LocalDate
    -0.45
    hloro
    -0.44
    OPTS
    -0.44
    POSITIVE LOGITS
    PreferredItem
    0.82
    ReusableCell
    0.81
    DoubleQuotes
    0.70
    providedIn
    0.69
     leaſt
    0.68
    ualla
    0.64
    APOLIS
    0.64
    tagHelperRunner
    0.64
    DockStyle
    0.64
    ſelves
    0.63
    Activations Density 2.957%

    No Known Activations