© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12526
    Prev
    Next
    INDEX
    Explanations

    words and phrases common in legal documents, especially those relating to court judgments and financial status.

    oai_token-act-pair · gemini-2.0-flash

    legal and financial matters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     ***!
    -0.91
     Wikimédia
    -0.82
     doubtnut
    -0.81
    DoubleQuotes
    -0.74
    AsUp
    -0.70
    sidemargin
    -0.69
     himo
    -0.69
    出版年
    -0.69
     Orrell
    -0.68
     HasFactory
    -0.68
    POSITIVE LOGITS
     للمعارف
    0.60
    <bos>
    0.59
    ணை
    0.45
    ungsver
    0.45
     الق
    0.44
    ционной
    0.44
     coming
    0.43
     estructura
    0.43
    ↵
    0.43
     saving
    0.43
    Activations Density 3.010%

    No Known Activations