© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9060
    Prev
    Next
    INDEX
    Explanations

    references to academic papers or figures

    oai_token-act-pair · gemini-2.0-flash

    technical terms or symbols

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

    scientific citations

    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
     кӀ
    -0.52
    pinMode
    -0.46
     nødven
    -0.46
    Unread
    -0.46
    InStock
    -0.45
    mampuan
    -0.45
     fær
    -0.45
    日閲覧
    -0.45
    legate
    -0.45
    diensten
    -0.45
    POSITIVE LOGITS
    usercontent
    0.69
     surla
    0.68
    esgue
    0.56
    ($__
    0.56
     resourceCulture
    0.56
     propOrder
    0.54
     Chwiliwch
    0.49
    انجليز
    0.49
    容
    0.49
    rungsseite
    0.49
    Activations Density 1.170%

    No Known Activations