© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5156
    Prev
    Next
    INDEX
    Explanations

    phrases related to caring for someone or something

    oai_token-act-pair · gemini-2.0-flash

    care

    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
    Negative Logits
     care
    -0.97
     Care
    -0.92
    Care
    -0.87
     cuidado
    -0.80
    care
    -0.79
     cared
    -0.76
     cuid
    -0.74
     caring
    -0.73
     CARE
    -0.72
     caretaker
    -0.71
    POSITIVE LOGITS
    DockStyle
    0.55
    tagHelperRunner
    0.54
    yargs
    0.54
    ujin
    0.51
    sizeCache
    0.51
    $_['
    0.49
    onViewCreated
    0.49
    NullException
    0.48
    ylla
    0.48
    RegistryLite
    0.48
    Activations Density 16.563%

    No Known Activations