© 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. 3951
    Prev
    Next
    INDEX
    Explanations

    code snippets and URLs

    oai_token-act-pair · gemini-2.0-flash

    code snippet

    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
     „
    -0.67
     "
    -0.67
     '
    -0.56
     “
    -0.52
     «
    -0.49
     ‚
    -0.49
     ‘
    -0.49
    љу
    -0.49
     виправивши
    -0.47
     `
    -0.47
    POSITIVE LOGITS
    AndEndTag
    1.00
    脚注の使い方
    0.80
     Normdatei
    0.79
    antMatchers
    0.76
     InputDecoration
    0.72
    PerformLayout
    0.69
    onViewCreated
    0.68
    SharedDtor
    0.66
     intStringLen
    0.66
     arşivlendi
    0.66
    Activations Density 3.751%

    No Known Activations