© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5537
    Prev
    Next
    INDEX
    Explanations

    uses of the word "and" and "to" in business, healthcare, and science contexts

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    :✨
    -1.02
     &___
    -0.95
    adaptiveStyles
    -0.88
    ,:);
    -0.85
     Jefus
    -0.82
    出版年
    -0.82
    ChildScrollView
    -0.79
     and
    -0.78
    ::~
    -0.78
    bootstrapcdn
    -0.77
    POSITIVE LOGITS
    alu
    0.42
     conta
    0.40
     sust
    0.39
    cal
    0.39
     Ersten
    0.39
     yet
    0.38
     vendar
    0.37
    њу
    0.36
    ässer
    0.36
     estre
    0.34
    Activations Density 10.088%

    No Known Activations