© 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. 5088
    Prev
    Next
    INDEX
    Explanations

    legal terms, especially those related to contracts and property

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     
    -0.42
    ,
    -0.40
    +
    -0.39
     San
    -0.39
     &
    -0.38
     De
    -0.38
     W
    -0.38
     ص
    -0.37
     (
    -0.36
    case
    -0.36
    POSITIVE LOGITS
     незавершена
    0.98
    ंदीखरीदारी
    0.95
     Majefty
    0.93
     Efq
    0.91
     ویکی‌پدیای
    0.87
    はじめに
    0.85
    Portale
    0.84
     myſelf
    0.81
     iſt
    0.81
     auffi
    0.80
    Activations Density 7.068%

    No Known Activations