© 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. 9878
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by other mathematical or scientific terminology

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "terms"

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

    terms

    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
    Lähteet
    -0.74
    AccessorTable
    -0.72
    Obrázky
    -0.67
    migrationBuilder
    -0.63
    IntoConstraints
    -0.57
     <<<<<<<<<<<<<<
    -0.55
     kaarangay
    -0.54
    iNdEx
    -0.52
     Exactos
    -0.52
    tilhar
    -0.52
    POSITIVE LOGITS
     terms
    3.27
    terms
    2.69
    Terms
    2.50
     Terms
    2.48
     TERMS
    2.34
     termes
    2.19
     term
    2.16
     términos
    2.11
    TERMS
    2.09
     terme
    1.89
    Activations Density 2.066%

    No Known Activations