© 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. 11013
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical or explicit descriptions

    oai_token-act-pair · gemini-2.0-flash

    vehicles and machines

    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
    Legends
    -0.71
     Legends
    -0.70
    Дереккөздер
    -0.70
     legends
    -0.69
    لينكات
    -0.68
    legends
    -0.67
     favorites
    -0.66
    OrBuilder
    -0.66
    出版年
    -0.64
     exceptions
    -0.63
    POSITIVE LOGITS
    Cars
    0.66
    Boats
    0.64
     Cars
    0.64
    Buses
    0.61
    schools
    0.61
     cars
    0.59
    buses
    0.59
     Buses
    0.58
    Films
    0.57
    Machines
    0.57
    Activations Density 2.704%

    No Known Activations