© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14156
    Prev
    Next
    INDEX
    Explanations

    words related to beauty and cosmetics

    oai_token-act-pair · gemini-2.0-flash

    beauty and cosmetics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Beauty
    -1.77
    Beauty
    -1.73
     beauty
    -1.65
     BEAUTY
    -1.57
    beauty
    -1.56
    BEAUTY
    -1.49
     cosmetic
    -1.34
     cosmetics
    -1.27
     Cosmetic
    -1.23
     Cosmetics
    -1.19
    POSITIVE LOGITS
    οιν
    0.59
     وصلة
    0.57
    WithMany
    0.50
     Membran
    0.50
    createServer
    0.49
    anyahu
    0.49
    GraphicsUnit
    0.48
     Aviv
    0.48
     membranes
    0.48
     Audiodateien
    0.47
    Activations Density 0.861%

    No Known Activations