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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13258
    Prev
    Next
    INDEX
    Explanations

    code displaying questions and answers

    oai_token-act-pair · gemini-2.0-flash

    code/data entries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
      
    -0.60
    豆
    -0.34
    op
    -0.33
    öbb
    -0.33
     throughout
    -0.32
     너
    -0.32
     ,
    -0.31
    JAKARTA
    -0.31
    би
    -0.31
    бия
    -0.31
    POSITIVE LOGITS
    sizeCache
    1.05
    DockStyle
    0.99
    
    0.90
     дописавши
    0.90
    RegressionTest
    0.90
    EDEFAULT
    0.84
     invokingState
    0.84
     surla
    0.83
    OGND
    0.82
    GEBURTSDATUM
    0.82
    Activations Density 2.959%

    No Known Activations