© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15395
    Prev
    Next
    INDEX
    Explanations

    the word "relative"

    oai_token-act-pair · gemini-2.0-flash

    relative

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    QMetaType
    -0.78
    principalTable
    -0.77
     Signalez
    -0.73
    kloped
    -0.72
     незавершена
    -0.72
    ніципа
    -0.69
    IndentedString
    -0.69
     HttpNotFound
    -0.67
    key
    -0.66
     key
    -0.66
    POSITIVE LOGITS
     linkovi
    0.47
     bağlantılar
    0.47
     contributions
    0.45
     profund
    0.44
    ว่า
    0.44
     shares
    0.44
    FilterChain
    0.43
     obe
    0.42
    новништво
    0.42
     positions
    0.42
    Activations Density 1.299%

    No Known Activations