© 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. 4384
    Prev
    Next
    INDEX
    Explanations

    a combination of trademarks and sigma beauty product titles

    oai_token-act-pair · gemini-2.0-flash

    Skincare products

    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
     Italijani
    -0.77
    DrawerToggle
    -0.68
    ColumnHeaders
    -0.63
    Abitanti
    -0.60
     fathoms
    -0.58
    Personensuche
    -0.57
    adpleegd
    -0.57
    eward
    -0.56
    PreferredItem
    -0.55
    inghouse
    -0.51
    POSITIVE LOGITS
     Serum
    0.56
    +#+#
    0.51
     Moisture
    0.50
     ciencia
    0.49
     pharmacie
    0.48
     Gel
    0.47
     OnInit
    0.46
     Hydration
    0.46
     kré
    0.46
    Serum
    0.46
    Activations Density 9.834%

    No Known Activations