© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6414
    Prev
    Next
    INDEX
    Explanations

    the job title of "engineer", sometimes in conjunction with other words such as "agreement", "endorsement", or "record"

    oai_token-act-pair · gemini-2.0-flash

    engineer

    np_max-act · gemini-2.0-flash

    engineer

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    存于互联网档案馆
    -0.74
     ‘
    -0.73
    ])){
    -0.69
    "):
    -0.68
     insuffisamment
    -0.67
     resourceCulture
    -0.67
    tical
    -0.67
     Ferr
    -0.67
    tige
    -0.67
     “
    -0.67
    POSITIVE LOGITS
     feroit
    1.31
     picioare
    1.30
     enfans
    1.29
     fermés
    1.23
     avoient
    1.23
     prêtres
    1.22
     colorés
    1.22
     dépens
    1.22
     ordinaires
    1.20
     noastre
    1.20
    Activations Density 3.651%

    No Known Activations