© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11716
    Prev
    Next
    INDEX
    Explanations

    java code syntax related to functions, arguments, and exceptions

    oai_token-act-pair · gemini-2.0-flash

    function signatures and exception handling

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

    )

    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
    хьтан
    -0.59
     Vikipedi
    -0.52
    луй
    -0.49
    arrêter
    -0.47
     tallied
    -0.46
     INCLUDED
    -0.46
     ghostly
    -0.45
    clero
    -0.43
     рее
    -0.43
     Costumes
    -0.43
    POSITIVE LOGITS
     throws
    0.90
     خارجية
    0.66
    ósitos
    0.62
    RectangleBorder
    0.59
    tvguidetime
    0.58
    richTextPanel
    0.56
     viewDidLoad
    0.55
    throws
    0.55
    brates
    0.55
    __":
    0.54
    Activations Density 0.265%

    No Known Activations