© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3278
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to accidents, injuries, or insurance claims

    oai_token-act-pair · gemini-2.0-flash

    Injury compensation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    InSection
    -0.77
    पया
    -0.74
    MemoryWarning
    -0.73
     OnInit
    -0.68
    sizeCache
    -0.62
     Vikipedi
    -0.62
     kaynağından
    -0.62
    )}</
    -0.61
    }}</
    -0.60
     peuples
    -0.60
    POSITIVE LOGITS
     safety
    0.49
    piram
    0.48
     risk
    0.47
     Safety
    0.44
    шому
    0.43
     mal
    0.42
    writeByte
    0.41
    ExceptionHandler
    0.41
    enburg
    0.41
     safely
    0.41
    Activations Density 1.765%

    No Known Activations