© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 168
    Prev
    Next
    INDEX
    Explanations

    information related to procedures, ethics, and legalities, usually in the context of a question

    oai_token-act-pair · gemini-2.0-flash

    FAQ/blog articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    UnitTesting
    -0.89
    fjspx
    -0.75
     Вікі
    -0.75
     linkovi
    -0.71
    IsMutable
    -0.66
     GenerationType
    -0.66
     utafitiHapana
    -0.65
    FieldBuilder
    -0.64
     Мексичка
    -0.60
    verwijspagina
    -0.60
    POSITIVE LOGITS
     faveur
    0.43
     posteriores
    0.41
     leggi
    0.41
    Дереккөздер
    0.41
    imiz
    0.41
     thoát
    0.40
     considér
    0.39
    hæng
    0.39
    alisasi
    0.39
     iguales
    0.39
    Activations Density 3.065%

    No Known Activations