© 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. 12695
    Prev
    Next
    INDEX
    Explanations

    words that describe opinions

    oai_token-act-pair · gemini-2.0-flash

    Complex, negative themes/opinions

    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
    GEBURTSDATUM
    -0.66
     générales
    -0.52
    ainville
    -0.50
    ulite
    -0.46
     sport
    -0.46
     utafiti
    -0.46
    idemiology
    -0.46
    balleur
    -0.46
     parlement
    -0.46
     spéciaux
    -0.45
    POSITIVE LOGITS
    oneofs
    0.73
    原始内容存档于
    0.62
     LoggerFactory
    0.61
    μή
    0.56
    iNdEx
    0.56
     StatefulWidget
    0.55
    UrlResolution
    0.55
    licet
    0.53
    "}"
    0.52
    ArgsConstructor
    0.52
    Activations Density 4.997%

    No Known Activations