© 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. 12545
    Prev
    Next
    INDEX
    Explanations

    computer architecture terminology, especially related to bits and processors

    oai_token-act-pair · gemini-2.0-flash

    variations of the term "bit"

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

    bit

    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
    #
    -0.68
    andoah
    -0.67
     ويكيميديا
    -0.66
    
    -0.65
    power
    -0.65
     '\\;'
    -0.60
    PreferredItem
    -0.58
     uintptr
    -0.56
    jsonwebtoken
    -0.55
    getInstance
    -0.54
    POSITIVE LOGITS
     bit
    0.91
    bit
    0.90
    Bit
    0.79
    BIT
    0.76
    bits
    0.71
     Bit
    0.71
     bits
    0.68
     Bits
    0.61
     BIT
    0.59
    Bits
    0.57
    Activations Density 2.640%

    No Known Activations