© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6577
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to quizzes and parsing of data

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "question"

    np_token-act-pair-logits · gpt-4o-mini

    question/questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     للمعارف
    -0.63
    AccessorTable
    -0.54
     otomatig
    -0.54
     myſelf
    -0.52
     Partagez
    -0.50
     SUDOC
    -0.50
    LVANIA
    -0.50
     perfons
    -0.48
     leaſt
    -0.48
    olastic
    -0.48
    POSITIVE LOGITS
     questions
    2.70
     question
    2.70
     Questions
    2.36
     Question
    2.36
    question
    2.22
    Question
    2.20
    questions
    2.20
    Questions
    2.16
     QUESTION
    2.08
     QUESTIONS
    2.05
    Activations Density 7.471%

    No Known Activations