© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15030
    Prev
    Next
    INDEX
    Explanations

    code 'break' statements and related 'default' keywords

    oai_token-act-pair · gemini-2.0-flash

    break

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    fasterxml
    -0.43
     cinematogra
    -0.41
    return
    -0.40
    NASDAQ
    -0.39
     simili
    -0.38
    Of
    -0.38
    hov
    -0.37
    ...
    -0.37
    do
    -0.37
     espac
    -0.37
    POSITIVE LOGITS
     مشين
    1.00
     يتيمه
    0.96
    évaluateur
    0.91
    featureID
    0.90
    mybatisplus
    0.88
     Савезне
    0.85
     ligiloj
    0.81
    tableFuture
    0.81
    */;
    0.79
     كومونز
    0.79
    Activations Density 0.215%

    No Known Activations