© 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. 9458
    Prev
    Next
    INDEX
    Explanations

    words or short phrases which describe actions of either scientific experimentation, appliance mechanism, or of a computer program.

    oai_token-act-pair · gemini-2.0-flash

    systems and processes

    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
    RegressionTest
    -1.05
    <bos>
    -0.95
    Portail
    -0.73
    SharedCtor
    -0.71
     oprot
    -0.70
    DockStyle
    -0.69
    GEBURTSDATUM
    -0.66
    MessageState
    -0.66
    KommentareTeilen
    -0.65
    ThemeOverlay
    -0.65
    POSITIVE LOGITS
    ourced
    0.57
     meditating
    0.55
     Profiling
    0.55
     inqui
    0.54
     firstly
    0.53
     knelt
    0.50
    STRUCTIONS
    0.50
     VALENT
    0.50
    weeted
    0.50
    hafte
    0.50
    Activations Density 12.493%

    No Known Activations