© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11610
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal disputes, code checking, and error handling

    oai_token-act-pair · gemini-2.0-flash

    PHP code

    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
     MonoBehaviour
    -0.76
     AppColors
    -0.72
    CreateMap
    -0.70
     nahilalakip
    -0.67
    
    -0.62
    tvguidetime
    -0.60
    WaitGroup
    -0.60
     rumours
    -0.58
    Aiheesta
    -0.57
     armoured
    -0.56
    POSITIVE LOGITS
     lack
    1.05
     failure
    1.02
     lacking
    0.98
     missing
    0.96
    Lack
    0.93
     Failure
    0.89
     manca
    0.88
    Failure
    0.87
     failed
    0.87
     failing
    0.86
    Activations Density 0.992%

    No Known Activations