© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14114
    Prev
    Next
    INDEX
    Explanations

    code snippets or fragments of code in various programming languages

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     propOrder
    -0.79
    Kjelder
    -0.76
     TextAppearance
    -0.74
     beginnetje
    -0.70
     Roskov
    -0.69
     referenties
    -0.67
    sizeCache
    -0.66
    🏼
    -0.65
     صوتيه
    -0.64
    🏽
    -0.64
    POSITIVE LOGITS
     /></
    0.59
    за
    0.55
     (£
    0.53
     oír
    0.52
     £
    0.51
     standing
    0.50
     relatório
    0.50
     spise
    0.49
     aanwezig
    0.48
    Clarity
    0.48
    Activations Density 0.141%

    No Known Activations