© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1850
    Prev
    Next
    INDEX
    Explanations

    references to being first

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "first"

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

    first

    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
     first
    -0.69
    first
    -0.67
     poveznice
    -0.60
     först
    -0.60
    ruptedException
    -0.59
     pertama
    -0.57
     första
    -0.56
    First
    -0.55
     First
    -0.50
     primero
    -0.50
    POSITIVE LOGITS
     Référence
    0.63
     timers
    0.62
     generation
    0.61
     Millennium
    0.61
    InputBorder
    0.60
    CppMethod
    0.56
    MemoryWarning
    0.54
     chi̍t
    0.54
     meeting
    0.53
     edition
    0.53
    Activations Density 2.154%

    No Known Activations