© 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. 15243
    Prev
    Next
    INDEX
    Explanations

    Java code syntax and keywords like "new", "class", and "Thread"

    oai_token-act-pair · gemini-2.0-flash

    say "("

    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
     sentiment
    -0.52
    =='
    -0.51
    โร
    -0.49
    ारे
    -0.48
    atra
    -0.47
     sell
    -0.47
     Slide
    -0.46
     حالی
    -0.46
     feeling
    -0.46
    сни
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.94
    rungsseite
    0.79
     الرياضيه
    0.73
     ModelExpression
    0.73
     kasarigan
    0.69
     betweenstory
    0.66
    AutoScaleMode
    0.64
    XmlAccessorType
    0.63
    InitVars
    0.62
     الحره
    0.60
    Activations Density 2.498%

    No Known Activations