© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9942
    Prev
    Next
    INDEX
    Explanations

    names, specifically likely Korean names with "Lee" and two-part given names

    oai_token-act-pair · gemini-2.0-flash

    Lee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ks
    -0.84
     Efq
    -0.73
     LEE
    -0.71
     ſmall
    -0.69
     AssemblyProduct
    -0.68
    ^(@)
    -0.68
     للاسماء
    -0.68
    ksha
    -0.66
     فريبيس
    -0.66
     diſt
    -0.66
    POSITIVE LOGITS
    <bos>
    0.85
    ContentAlignment
    0.59
     <<<<<<<<<<<<<<
    0.54
    XtraReports
    0.49
     diting
    0.47
     föl
    0.45
    ISupport
    0.44
    IBOutlet
    0.43
    UnknownFieldSet
    0.42
    ’
    0.42
    Activations Density 1.943%

    No Known Activations