© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1035
    Prev
    Next
    INDEX
    Explanations

    references to a legal system and/or being above the law

    oai_token-act-pair · gemini-2.0-flash

    law and legal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    WaitGroup
    -0.49
    ToTensor
    -0.40
     mergeFrom
    -0.39
    териалы
    -0.39
    Vanjske
    -0.39
    例文帳に追加
    -0.39
    ср
    -0.38
    ersonic
    -0.37
    ственный
    -0.36
    ناد
    -0.36
    POSITIVE LOGITS
     law
    2.42
     Law
    2.05
    law
    1.99
    Law
    1.94
     LAW
    1.91
     laws
    1.91
    LAW
    1.78
     legal
    1.77
     Laws
    1.70
    Laws
    1.63
    Activations Density 1.779%

    No Known Activations