© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 87
    Prev
    Next
    INDEX
    Explanations

    words related to business, official organizations, disclaimers, technical information and health

    oai_token-act-pair · gemini-2.0-flash

    boilerplate

    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
    ificada
    -0.46
    cheinend
    -0.44
     Publicar
    -0.44
    ชา
    -0.44
    eron
    -0.43
    fgaben
    -0.43
    OSSARY
    -0.42
     paru
    -0.42
    częściej
    -0.41
    ąc
    -0.41
    POSITIVE LOGITS
    webElementXpaths
    0.98
     beginnetje
    0.98
    LookAnd
    0.87
    FormTagHelper
    0.83
     AssemblyProduct
    0.79
    PerformLayout
    0.79
     للاسماء
    0.78
    expandindo
    0.76
    InjectAttribute
    0.76
    yntaxException
    0.75
    Activations Density 54.177%

    No Known Activations