© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1429
    Prev
    Next
    INDEX
    Explanations

    positive language that describes a product

    oai_token-act-pair · gemini-2.0-flash

    car and tech 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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     للاسماء
    -0.66
    GOTREF
    -0.62
    featureID
    -0.60
    CompleteListener
    -0.60
    FunctionFlags
    -0.58
    Referanser
    -0.57
     مرئيه
    -0.56
    unknownFields
    -0.54
    OGND
    -0.54
    Controllo
    -0.54
    POSITIVE LOGITS
    protoimpl
    0.47
     bezig
    0.46
    teken
    0.42
    참고
    0.42
    ėtų
    0.42
    cub
    0.42
    IDF
    0.42
     tasa
    0.41
     Wicidata
    0.41
    setupUi
    0.40
    Activations Density 8.067%

    No Known Activations