© 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. 4100
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings, especially concerning knowledge, contracts, and fraud

    oai_token-act-pair · gemini-2.0-flash

    knowledge

    np_max-act · gemini-2.0-flash

    knowledge

    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
    principalColumn
    -0.61
     revés
    -0.58
    NameInMap
    -0.55
     Usual
    -0.50
    InSection
    -0.50
     inférieur
    -0.49
    ázka
    -0.48
    WireFormatLite
    -0.47
    antal
    -0.47
    cié
    -0.47
    POSITIVE LOGITS
     שוליים
    0.60
     فريبيس
    0.58
    versy
    0.54
    GEBURTSDATUM
    0.54
     старости
    0.49
     كومونز
    0.49
    verwijspagina
    0.48
    ActionCreators
    0.48
     légale
    0.48
     HttpNotFound
    0.48
    Activations Density 3.535%

    No Known Activations