© 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. 10769
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is wishing someone else well either in a business or personal context

    oai_token-act-pair · gemini-2.0-flash

    company-related terms

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

    best wishes

    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
     Reverso
    -0.43
    abra
    -0.42
     halv
    -0.42
    ígen
    -0.41
    ולוג
    -0.41
    cycline
    -0.40
    CustomAttributes
    -0.40
    不定
    -0.40
    Sil
    -0.40
    ঞ
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    0.94
    ArrowToggle
    0.91
    RenderAtEndOf
    0.88
     ویکی‌پدی
    0.85
    ReusableCell
    0.82
     становника
    0.82
    ValueStyle
    0.81
    évaluateur
    0.79
    hoeddwyd
    0.79
     betweenstory
    0.76
    Activations Density 0.769%

    No Known Activations