© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13092
    Prev
    Next
    INDEX
    Explanations

    dialogue and phrases indicating contemplation

    oai_token-act-pair · gemini-2.0-flash

    first person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Waray
    -0.74
     ujednoznacz
    -0.70
     SqlParameter
    -0.68
    verwijspagina
    -0.65
    InputBorder
    -0.64
    MENAFN
    -0.63
    rawDesc
    -0.63
    QFont
    -0.62
     AssemblyCompany
    -0.60
    XMLSchema
    -0.60
    POSITIVE LOGITS
     disparition
    0.43
     însă
    0.42
    SpringBootTest
    0.41
     empfind
    0.39
     Progressives
    0.39
    المناصب
    0.38
    nodeValue
    0.38
     Natuur
    0.38
     Prometheus
    0.38
     magnes
    0.38
    Activations Density 0.148%

    No Known Activations