© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14920
    Prev
    Next
    INDEX
    Explanations

    words related to time, careers and professional sports

    oai_token-act-pair · gemini-2.0-flash

    full

    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
    出版年
    -0.67
     IBOutlet
    -0.66
    esgue
    -0.61
    textTheme
    -0.60
     onAnimation
    -0.60
     geldig
    -0.59
     doInBackground
    -0.59
    TypedDataSet
    -0.59
    ècie
    -0.57
    WaitGroup
    -0.57
    POSITIVE LOGITS
     full
    3.27
    full
    2.83
     Full
    2.75
    Full
    2.72
    FULL
    2.33
     FULL
    2.28
     peł
    1.73
    フル
    1.73
     vollen
    1.61
     penuh
    1.55
    Activations Density 3.364%

    No Known Activations