© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4257
    Prev
    Next
    INDEX
    Explanations

    words related to opinions in the context of movie, book, or art reviews.

    oai_token-act-pair · gemini-2.0-flash

    film and book reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     retraite
    -0.58
     EconPapers
    -0.54
     Matériau
    -0.52
     humains
    -0.47
    Character
    -0.47
     Character
    -0.47
    expandindo
    -0.47
     című
    -0.46
     carreira
    -0.45
     mukana
    -0.45
    POSITIVE LOGITS
     RouterModule
    0.67
    protoc
    0.65
    ConstraintMaker
    0.62
    FXMLLoader
    0.61
     isInitialized
    0.60
    SharedDtor
    0.60
     للمعارف
    0.59
    XmlEnum
    0.58
    twimg
    0.57
     ProtoMessage
    0.57
    Activations Density 12.856%

    No Known Activations