© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14843
    Prev
    Next
    INDEX
    Explanations

    uses of the word "this" and articles like "a", "an", "the" when they begin a novel thought

    oai_token-act-pair · gemini-2.0-flash

    demonstrative pronouns and articles

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

    this

    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
     allmän
    -0.58
    Tembelea
    -0.57
     découver
    -0.57
     graisse
    -0.57
     foglie
    -0.57
     chimiques
    -0.56
    StructEnd
    -0.55
     judiciales
    -0.55
     steder
    -0.54
     siinä
    -0.54
    POSITIVE LOGITS
     type
    0.69
     particular
    0.63
     uska
    0.62
    yntaxException
    0.61
    ieten
    0.56
    出版年
    0.54
    erals
    0.52
     Booth
    0.52
    entile
    0.51
    particular
    0.50
    Activations Density 9.785%

    No Known Activations