© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1904
    Prev
    Next
    INDEX
    Explanations

    code comments about when a file was created

    oai_token-act-pair · gemini-2.0-flash

    text indicating authorship or creation

    np_token-act-pair-logits · gpt-4o-mini

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cwt
    -0.66
    DebuggerNonUser
    -0.64
     [?]
    -0.62
    webElementXpaths
    -0.61
     <<<<<<<<<<<<<<
    -0.61
     themſelves
    -0.60
     InputDecoration
    -0.60
    theless
    -0.60
    Демографія
    -0.59
    AsyncResult
    -0.59
    POSITIVE LOGITS
     by
    0.88
     kasarigan
    0.71
     oleh
    0.65
     By
    0.59
     توسط
    0.56
     przez
    0.56
    By
    0.55
     in
    0.54
     December
    0.52
    by
    0.50
    Activations Density 1.259%

    No Known Activations