© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3715
    Prev
    Next
    INDEX
    Explanations

    words about marketing and e-commerce and the user experience

    oai_token-act-pair · gemini-2.0-flash

    brand

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     tartalomajánló
    -0.98
     propOrder
    -0.73
    Geplaatst
    -0.67
    GEBURTSDATUM
    -0.65
    .*")]
    -0.65
     Réponses
    -0.65
    DockStyle
    -0.63
    yntaxException
    -0.61
     unknownFields
    -0.57
     Độ
    -0.57
    POSITIVE LOGITS
     brand
    2.72
    brand
    2.23
     Brand
    2.16
    Brand
    2.11
     BRAND
    1.91
    BRAND
    1.65
    品牌
    1.32
     brands
    1.27
     marchio
    1.20
    ブランド
    1.17
    Activations Density 2.011%

    No Known Activations