© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3796
    Prev
    Next
    INDEX
    Explanations

    text from published research papers, articles, and professional reports

    oai_token-act-pair · gemini-2.0-flash

    symbols punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    oflavin
    -0.47
     samoz
    -0.44
    exits
    -0.44
    عدم
    -0.43
     comunes
    -0.42
    unków
    -0.39
    Karten
    -0.39
    ゴリー
    -0.38
    rump
    -0.38
    qualität
    -0.37
    POSITIVE LOGITS
    <bos>
    1.03
     Мексичка
    0.78
     EconPapers
    0.75
     WaitForSeconds
    0.70
    tvguidetime
    0.69
     NSCoder
    0.67
    ChildScrollView
    0.66
    CppCodeGen
    0.66
     ControllerBase
    0.66
    tableFuture
    0.65
    Activations Density 12.427%

    No Known Activations