© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12038
    Prev
    Next
    INDEX
    Explanations

    the Java Swing UI framework

    oai_token-act-pair · gemini-2.0-flash

    swing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Monfieur
    -2.30
     Majefty
    -2.23
     itſelf
    -2.17
     myſelf
    -2.13
     Houſe
    -2.11
     Jefus
    -2.08
     pleaſure
    -2.08
     Efq
    -2.06
     houſe
    -2.06
     himſelf
    -2.06
    POSITIVE LOGITS
    ↵↵
    1.28
     
    1.15
    ↵
    1.02
     I
    0.94
     (
    0.94
    <eos>
    0.93
      
    0.91
     -
    0.89
    s
    0.88
     A
    0.87
    Activations Density 1.355%

    No Known Activations