© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10929
    Prev
    Next
    INDEX
    Explanations

    words in legal documents related to case details, government, and potential discrimination

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    脚注の使い方
    -1.59
    TagMode
    -1.51
     كومونز
    -1.46
    
    -1.45
     الحره
    -1.45
    expandindo
    -1.44
    ReusableCell
    -1.43
     חיצוניים
    -1.41
     ―――――
    -1.41
    DockStyle
    -1.40
    POSITIVE LOGITS
     in
    0.39
     to
    0.38
     is
    0.32
     of
    0.29
     a
    0.28
     &
    0.19
    &
    0.19
    </i>
    0.18
     as
    0.17
     for
    0.17
    Activations Density 8.031%

    No Known Activations