© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9221
    Prev
    Next
    INDEX
    Explanations

    words that would occur in publications, technical documents or datasheets

    oai_token-act-pair · gemini-2.0-flash

    chamber

    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
    hach
    -0.56
    VersionUID
    -0.53
    inth
    -0.51
    ARSE
    -0.51
     BrowserModule
    -0.50
    NewLabel
    -0.50
    athread
    -0.50
    AxisAlignment
    -0.50
     setData
    -0.47
    ichtliche
    -0.47
    POSITIVE LOGITS
    <bos>
    2.38
    GEBURTSDATUM
    0.81
     Савезне
    0.68
     '\\;'
    0.66
    IUrlHelper
    0.63
    MigrationBuilder
    0.61
     Paglinawan
    0.59
    afficheront
    0.57
    #
    0.57
     ویکی‌پدی
    0.57
    Activations Density 27.526%

    No Known Activations