© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6378
    Prev
    Next
    INDEX
    Explanations

    the names of Java libraries, especially Swing and AWT

    oai_token-act-pair · gemini-2.0-flash

    Java swing code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     himſelf
    -0.52
     myſelf
    -0.51
     Efq
    -0.48
    $',
    -0.48
    $.
    -0.47
    felves
    -0.47
    ^(@)
    -0.45
     themſelves
    -0.44
    {}'.
    -0.42
     itſelf
    -0.42
    POSITIVE LOGITS
    stateProvider
    0.75
    mybatisplus
    0.70
    BindView
    0.70
    AntiForgeryToken
    0.67
     TextInputType
    0.66
     onAnimation
    0.66
     BitmapFactory
    0.64
     JScrollPane
    0.64
     DialogInterface
    0.63
    StoreMessageInfo
    0.62
    Activations Density 2.342%

    No Known Activations