© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 10137
    Prev
    Next
    INDEX
    Explanations

    hyphenated words or words with a prefix

    oai_token-act-pair · gemini-2.0-flash

    Prefixes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.57
    val
    -0.53
    Comma
    -0.48
    for
    -0.47
    github
    -0.47
    console
    -0.46
     Walker
    -0.46
     Siete
    -0.45
     Ten
    -0.45
    ph
    -0.45
    POSITIVE LOGITS
     GenerationType
    0.86
     مرئيه
    0.86
     متعلقه
    0.80
    aarrggbb
    0.78
     betweenstory
    0.77
     calendriers
    0.74
    MessageTagHelper
    0.72
    RenderAtEndOf
    0.71
     Extragalactic
    0.69
    URLException
    0.66
    Activations Density 1.155%

    No Known Activations