© 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. 9664
    Prev
    Next
    INDEX
    Explanations

    mentions of "Mario Badescu" and/or coupon codes.

    oai_token-act-pair · gemini-2.0-flash

    Skincare/cosmetic product descriptions

    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
    +#+#
    -0.64
    closePath
    -0.49
    ViewImports
    -0.48
     Reverso
    -0.47
     Lombardo
    -0.46
    RUnlock
    -0.45
     orec
    -0.45
     schedules
    -0.44
    Geografía
    -0.44
     frigor
    -0.43
    POSITIVE LOGITS
     Concentrate
    0.60
     يتيمه
    0.58
    észetes
    0.58
    PreferredItem
    0.54
     незавершена
    0.54
    󠁴
    0.54
     Toner
    0.54
     européennes
    0.53
    InjectAttribute
    0.52
     Вікі
    0.52
    Activations Density 3.921%

    No Known Activations