© 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. 4482
    Prev
    Next
    INDEX
    Explanations

    dates and months

    oai_token-act-pair · gemini-2.0-flash

    dates

    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
    IntoConstraints
    -0.87
     IOError
    -0.80
     AssemblyCompany
    -0.73
    APOLIS
    -0.73
    onAttach
    -0.72
     IBOutlet
    -0.71
    yntaxException
    -0.70
    DOCTYPE
    -0.70
    GenerationType
    -0.69
    DrawerToggle
    -0.69
    POSITIVE LOGITS
     times
    0.47
    <bos>
    0.45
     
    0.45
    省市镇
    0.43
     full
    0.41
     time
    0.40
     '\\;'
    0.40
    分的
    0.39
    full
    0.39
     propri
    0.38
    Activations Density 2.565%

    No Known Activations