© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8183
    Prev
    Next
    INDEX
    Explanations

    words that are tags in HTML or URLs

    oai_token-act-pair · gemini-2.0-flash

    HTML tag bold

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <eos>
    -0.62
    NameInMap
    -0.61
      (
    -0.59
     Dickerson
    -0.54
     or
    -0.53
     far
    -0.52
     виправивши
    -0.51
     is
    -0.50
    olulu
    -0.49
     La
    -0.48
    POSITIVE LOGITS
     itſelf
    0.88
     Sopho
    0.82
     myſelf
    0.76
     photolibrary
    0.73
     Audiodateien
    0.72
     ovp
    0.72
     समीक्षक
    0.71
    CppCodeGen
    0.71
     CJK
    0.71
     Cæsar
    0.70
    Activations Density 3.554%

    No Known Activations