© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13457
    Prev
    Next
    INDEX
    Explanations

    positive descriptions, particularly those related to writing or presenting

    oai_token-act-pair · gemini-2.0-flash

    Positive emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     AssemblyCulture
    -0.83
     tartalomajánló
    -0.80
    WithIOException
    -0.78
     فريبيس
    -0.76
     Мексичка
    -0.75
     Paglinawan
    -0.72
     ویکی‌پدیا
    -0.71
    :✨
    -0.70
    RenderAtEndOf
    -0.70
    tvguidetime
    -0.69
    POSITIVE LOGITS
     pleasure
    1.96
    pleasure
    1.65
     Pleasure
    1.40
     joy
    1.26
     privilege
    1.25
     plaisir
    1.25
     delight
    1.13
     honor
    1.13
     pleasures
    1.10
     PLEAS
    1.10
    Activations Density 1.171%

    No Known Activations