© 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. 14203
    Prev
    Next
    INDEX
    Explanations

    the beginnings of code blocks in Java source files

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms

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

    Java 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_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
     Nova
    -0.40
     owe
    -0.38
     in
    -0.38
     lentes
    -0.38
     Lak
    -0.38
    ținut
    -0.37
     Lar
    -0.37
     wrong
    -0.37
    ScreenState
    -0.37
     dibanding
    -0.36
    POSITIVE LOGITS
     pageContext
    0.77
    WriteBarrier
    0.75
     myſelf
    0.71
    ſelf
    0.70
    CloseOperation
    0.68
    出版年
    0.67
     AssemblyTitle
    0.67
    ſelves
    0.66
     referrerpolicy
    0.66
    GEBURTSDATUM
    0.64
    Activations Density 0.482%

    No Known Activations