© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10885
    Prev
    Next
    INDEX
    Explanations

    language related to economics and business, often of a local nature

    oai_token-act-pair · gemini-2.0-flash

    Locations and areas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    +:+
    -0.55
    otriz
    -0.48
    PropertyChanged
    -0.47
     vinto
    -0.47
     scattata
    -0.47
     nhat
    -0.46
     passés
    -0.45
    store
    -0.45
     store
    -0.45
     Italijanski
    -0.44
    POSITIVE LOGITS
    AndEndTag
    0.78
     незавершена
    0.73
    extAlignment
    0.70
     surgeries
    0.64
    cdef
    0.60
    GraphicsUnit
    0.60
    таратура
    0.59
    sidemargin
    0.56
    invokeLater
    0.56
    RegistryLite
    0.55
    Activations Density 1.297%

    No Known Activations