© 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. 4483
    Prev
    Next
    INDEX
    Explanations

    discourse markers and sentence connectors.

    oai_token-act-pair · gemini-2.0-flash

    conditional words

    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
    <bos>
    -0.78
    曖昧さ回避
    -0.56
    />,
    -0.52
    といって
    -0.48
    ValueStyle
    -0.47
     pulumi
    -0.47
     đương
    -0.47
     SCHEME
    -0.45
     通販
    -0.45
    bardziej
    -0.45
    POSITIVE LOGITS
    kmale
    0.68
     CreateTagHelper
    0.57
    UnknownFields
    0.56
    DotNetBar
    0.55
    PerformLayout
    0.54
     Vikipedi
    0.54
    jectures
    0.52
    espec
    0.52
     CONDU
    0.51
    autant
    0.51
    Activations Density 13.512%

    No Known Activations