© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13263
    Prev
    Next
    INDEX
    Explanations

    the word "right" used as an adjective

    oai_token-act-pair · gemini-2.0-flash

    keywords related to correctness or appropriateness

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

    right

    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
     for
    -0.60
     adequad
    -0.56
     nzuri
    -0.54
     meilleures
    -0.52
     good
    -0.50
     meilleure
    -0.47
     untuk
    -0.47
     stessi
    -0.46
     migliore
    -0.46
     mauvaise
    -0.45
    POSITIVE LOGITS
     propOrder
    1.11
     AssemblyCulture
    1.08
    Tikang
    0.77
    RunWith
    0.77
    DataAnnotations
    0.75
     CreateTagHelper
    0.74
    ItemBackground
    0.73
    __":
    0.71
    __":
    0.70
    AutoresizingMask
    0.69
    Activations Density 3.148%

    No Known Activations