© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3339
    Prev
    Next
    INDEX
    Explanations

    words commonly used in legal documents related to courts, defendants, and legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    court

    np_max-act · gemini-2.0-flash

    court

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     صوتيه
    -0.71
    ArrowToggle
    -0.61
     culturelles
    -0.54
    mities
    -0.52
     forState
    -0.52
    Condol
    -0.52
    cence
    -0.47
    tical
    -0.47
     culturale
    -0.46
    せっかく
    -0.45
    POSITIVE LOGITS
    <bos>
    0.72
     ioutil
    0.66
     BoxFit
    0.59
     saites
    0.57
    RefNanny
    0.57
    ziasztok
    0.56
     tartalomajánló
    0.56
     Oblast
    0.55
    ArgumentParser
    0.54
    pédie
    0.54
    Activations Density 3.978%

    No Known Activations