© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9099
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to parents and children, particularly regarding communication, discipline, and understanding

    oai_token-act-pair · gemini-2.0-flash

    encouragement and understanding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     disambiguazione
    -0.81
     <>",
    -0.78
     Référence
    -0.73
    expandindo
    -0.70
    Datuak
    -0.70
    __*/
    -0.70
    İstinadlar
    -0.68
     oprot
    -0.67
    Aiheesta
    -0.66
    存于互联网档案馆
    -0.66
    POSITIVE LOGITS
     understood
    0.57
     understands
    0.48
    чув
    0.48
     entendido
    0.46
     zich
    0.45
     appreciated
    0.45
     ajudá
    0.45
     mengerti
    0.44
     grossesse
    0.43
     sentirse
    0.43
    Activations Density 1.717%

    No Known Activations