© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15679
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    Legal and judicial actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    -0.88
    mybatisplus
    -0.81
     للمعارف
    -0.79
    ValueStyle
    -0.79
     HasFactory
    -0.76
    ConstraintMaker
    -0.73
     ModelExpression
    -0.71
    تقاوى
    -0.71
     esternos
    -0.70
    MLLoader
    -0.70
    POSITIVE LOGITS
     actions
    0.65
     acts
    0.60
     intervention
    0.60
     interference
    0.60
     act
    0.59
     action
    0.57
    actions
    0.57
     rene
    0.54
     acted
    0.54
    acted
    0.53
    Activations Density 3.448%

    No Known Activations