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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11768
    Prev
    Next
    INDEX
    Explanations

    personal pronouns

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'better'

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

    Translations of "better"

    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
    GEBURTSDATUM
    -0.66
    RenderAtEndOf
    -0.64
     propOrder
    -0.63
    WebElementEntity
    -0.62
    msgTypes
    -0.62
     незавершена
    -0.61
    addCriterion
    -0.61
    جغرافيا
    -0.60
    thâu
    -0.59
     wireType
    -0.57
    POSITIVE LOGITS
     better
    3.17
    better
    2.94
    Better
    2.66
     Better
    2.55
     BETTER
    2.38
     mejor
    2.16
     mieux
    2.11
     besser
    2.09
     melhor
    2.06
     meglio
    1.98
    Activations Density 1.536%

    No Known Activations