© 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. 4272
    Prev
    Next
    INDEX
    Explanations

    text in academic literature

    oai_token-act-pair · gemini-2.0-flash

    scientific texts

    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
    ‌است
    -0.63
     Majefty
    -0.62
     himſelf
    -0.60
     pinulongan
    -0.59
     dignité
    -0.58
     themſelves
    -0.57
     calça
    -0.57
    깥
    -0.57
     auffi
    -0.57
     CommandType
    -0.57
    POSITIVE LOGITS
    دانشنامهٔ
    0.59
     везе
    0.58
    ChildScrollView
    0.57
     Chwiliwch
    0.56
    嘧
    0.56
    rag
    0.52
    RegressionTest
    0.51
     nice
    0.51
     really
    0.50
     ویکی‌پدی
    0.50
    Activations Density 48.515%

    No Known Activations