© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9808
    Prev
    Next
    INDEX
    Explanations

    the names of fonts and related typography terms

    oai_token-act-pair · gemini-2.0-flash

    font-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     actionMode
    -0.65
     Процитовано
    -0.58
    felizmente
    -0.53
    omonas
    -0.53
     arşivlendi
    -0.52
    BindView
    -0.52
     makeStyles
    -0.51
     myco
    -0.50
     AllAfrica
    -0.50
     transparence
    -0.50
    POSITIVE LOGITS
    出版年
    0.57
     pro
    0.54
    ValueGeneration
    0.51
     blessés
    0.49
    ={`/
    0.48
     Pro
    0.47
     通販
    0.47
     AssemblyProduct
    0.47
     يتيمه
    0.46
    работ
    0.45
    Activations Density 1.124%

    No Known Activations