© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10169
    Prev
    Next
    INDEX
    Explanations

    language related to legal reasoning regarding regulations

    oai_token-act-pair · gemini-2.0-flash

    Regulations/Guidelines/Rules

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    expandindo
    -0.67
     createState
    -0.56
    DataAnnotations
    -0.54
    Parameteri
    -0.54
    ftagPool
    -0.54
     internetowa
    -0.52
    WaitGroup
    -0.48
    estras
    -0.48
    PMailer
    -0.47
     PhpStorm
    -0.46
    POSITIVE LOGITS
    buttonBar
    0.64
     الحره
    0.59
     AssemblyCulture
    0.55
     temporales
    0.54
     remp
    0.51
    VIAF
    0.50
    basicConfig
    0.50
    Executive
    0.50
    omiast
    0.47
     وتسجيلات
    0.47
    Activations Density 1.625%

    No Known Activations