© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15019
    Prev
    Next
    INDEX
    Explanations

    text related to legal documents and court proceedings

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with certain prefixes like '▁'

    np_token-act-pair-logits · gpt-4o-mini

    Legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Мексичка
    -0.86
     itſelf
    -0.83
    RectangleBorder
    -0.82
     Anſ
    -0.81
     cdti
    -0.81
     <=",
    -0.81
     quadrature
    -0.79
     myſelf
    -0.79
     Phry
    -0.79
     raiſ
    -0.78
    POSITIVE LOGITS
     it
    0.51
     he
    0.49
     on
    0.48
     via
    0.47
    וויק
    0.45
     er
    0.44
     its
    0.44
     $\
    0.43
     var
    0.43
     H
    0.43
    Activations Density 2.441%

    No Known Activations