© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6632
    Prev
    Next
    INDEX
    Explanations

    the word "one" and the letters 'a' and 'A'

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'one'

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

    one

    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
     one
    -2.92
    one
    -1.88
     één
    -1.71
     unul
    -1.61
    One
    -1.59
     один
    -1.59
     uno
    -1.58
     یکی
    -1.54
     jednej
    -1.50
     одна
    -1.46
    POSITIVE LOGITS
    enterOuterAlt
    0.67
    twimg
    0.64
    ərbaycan
    0.58
    OrNil
    0.57
     sola
    0.57
    الحياه
    0.56
     betweenstory
    0.55
    InSection
    0.54
    windowFixed
    0.54
     surla
    0.54
    Activations Density 2.173%

    No Known Activations