© 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. 9742
    Prev
    Next
    INDEX
    Explanations

    strings of initials with dots, possibly representing author names in academic citations

    oai_token-act-pair · 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
     doce
    -0.49
    ้าง
    -0.49
     ipc
    -0.48
     asupra
    -0.48
     Forumite
    -0.47
    hoch
    -0.46
     over
    -0.46
    ARTE
    -0.43
    ními
    -0.43
    uesia
    -0.43
    POSITIVE LOGITS
    Tembelea
    1.07
     CreateTagHelper
    0.75
    GEBURTSDATUM
    0.75
    InjectAttribute
    0.74
    AnchorStyles
    0.73
    ंदीखरीदारी
    0.73
     Bioaccumulative
    0.69
     viewDidLoad
    0.68
     AssemblyProduct
    0.68
    Билгалдахарш
    0.67
    Activations Density 0.827%

    No Known Activations