© 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. 6467
    Prev
    Next
    INDEX
    Explanations

    a mix of programming code snippets, and possibly some keywords and identifiers within that code.

    oai_token-act-pair · gemini-2.0-flash

    terms related to programming and testing

    np_token-act-pair-logits · gpt-4o-mini
    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
    insee
    -0.61
     invokingState
    -0.49
    resave
    -0.48
     rés
    -0.48
    الا
    -0.48
    selectBy
    -0.47
    twimg
    -0.47
    setTotal
    -0.46
    hler
    -0.45
    ThroughAttribute
    -0.45
    POSITIVE LOGITS
    RegressionTest
    0.76
     مشين
    0.64
    chism
    0.61
     חיצוניים
    0.60
    رشف
    0.59
     initComponents
    0.58
    CloseOperation
    0.54
     Deber
    0.53
    "):
    0.53
    AndEndTag
    0.52
    Activations Density 4.045%

    No Known Activations