© 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. 9900
    Prev
    Next
    INDEX
    Explanations

    words and symbols used in scientific equations

    oai_token-act-pair · gemini-2.0-flash

    x

    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
    AccessorTable
    -0.82
    DoubleQuotes
    -0.75
    MessageTagHelper
    -0.70
     nakalista
    -0.65
    BufferException
    -0.65
    rungsseite
    -0.59
    bootstrapcdn
    -0.58
    GHIJKLM
    -0.57
    LEncoder
    -0.57
    tagHelper
    -0.57
    POSITIVE LOGITS
     x
    2.89
    x
    2.48
     X
    1.94
    X
    1.74
    ×
    1.66
    ｘ
    1.63
     ×
    1.61
    xx
    1.40
     х
    1.35
    𝑥
    1.32
    Activations Density 3.646%

    No Known Activations