© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12534
    Prev
    Next
    INDEX
    Explanations

    the phrase "take care of"

    oai_token-act-pair · gemini-2.0-flash

    of

    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
     المعيارى
    -0.95
    IsContent
    -0.81
    MLLoader
    -0.79
    )\}
    -0.77
     shepherd
    -0.75
    AsUp
    -0.75
    agissait
    -0.72
     shepherds
    -0.72
     InputDecoration
    -0.71
    })*/
    -0.69
    POSITIVE LOGITS
     Schilling
    0.48
     gång
    0.45
     ১
    0.42
     terbuka
    0.42
     margen
    0.42
    initComponents
    0.41
     fratelli
    0.40
    throw
    0.40
    RegistryLite
    0.40
     J
    0.40
    Activations Density 0.368%

    No Known Activations