© 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. 10639
    Prev
    Next
    INDEX
    Explanations

    legal jargon, specifically terms related to court proceedings and legal obligations

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash
    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
    <bos>
    -0.59
     blí
    -0.50
     maß
    -0.47
     arreglos
    -0.47
     ragioni
    -0.47
     renfor
    -0.46
    iconque
    -0.46
     versiones
    -0.45
     sahiptir
    -0.44
    ที่สุด
    -0.43
    POSITIVE LOGITS
    ViewFeatures
    0.95
    AccessorTable
    0.78
    تقاوى
    0.70
    IBarButtonItem
    0.69
    protoimpl
    0.69
     CreateTagHelper
    0.67
     initComponents
    0.67
    EndProject
    0.65
    StoryboardSegue
    0.65
    évaluateur
    0.65
    Activations Density 2.905%

    No Known Activations