© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3024
    Prev
    Next
    INDEX
    Explanations

    Java and javax library import statements and related class definitions

    oai_token-act-pair · gemini-2.0-flash

    Java programming elements

    np_token-act-pair-logits · gpt-4o-mini

    java

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     resourceCulture
    -0.85
     doInBackground
    -0.72
    detectChanges
    -0.66
    ThroughAttribute
    -0.66
    PageRoute
    -0.63
     AssemblyVersion
    -0.62
    
    -0.61
    IBarButtonItem
    -0.60
    parsedMessage
    -0.60
    Бахар
    -0.59
    POSITIVE LOGITS
     Tagged
    0.49
    OrBuilder
    0.48
    ändler
    0.44
     Nef
    0.42
     skippy
    0.42
    🇱
    0.41
     SqlDbType
    0.40
     reb
    0.40
     pai
    0.39
    дян
    0.39
    Activations Density 1.101%

    No Known Activations