© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8866
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "query" and related terms, especially in the context of programming and web development

    oai_token-act-pair · gemini-2.0-flash

    query

    np_max-act · gemini-2.0-flash

    Query

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    liferay
    -0.58
    Path
    -0.54
     slo
    -0.52
    box
    -0.51
     path
    -0.50
    path
    -0.50
    "))
    -0.50
    兮
    -0.50
    */)
    -0.48
    }")
    -0.47
    POSITIVE LOGITS
     ſtill
    0.81
     Khrushchev
    0.77
    GraphicsUnit
    0.73
     Efq
    0.71
     bezeichneter
    0.69
     doInBackground
    0.69
     myſelf
    0.69
    NewGuid
    0.68
     themſelves
    0.66
     florales
    0.66
    Activations Density 1.316%

    No Known Activations