© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3564
    Prev
    Next
    INDEX
    Explanations

    the word "first" in contexts related to anniversaries

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    новништво
    -0.62
     समीक्षक
    -0.61
     vitesses
    -0.55
    PyExc
    -0.54
    łaszcza
    -0.51
    <bos>
    -0.50
     IOM
    -0.47
    Билгалдахарш
    -0.46
     manutenzione
    -0.46
     tasche
    -0.45
    POSITIVE LOGITS
     betweenstory
    0.70
    InjectAttribute
    0.66
    principalTable
    0.63
     дописавши
    0.63
    ContentAsync
    0.62
    出版年
    0.58
     فريبيس
    0.53
    adaptiveStyles
    0.53
    reportWebVitals
    0.52
    AnimationsModule
    0.52
    Activations Density 0.908%

    No Known Activations