© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11303
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to online content or digital media

    oai_token-act-pair · gemini-2.0-flash

    content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     content
    -1.78
     Content
    -1.49
    Content
    -1.48
    content
    -1.46
     contents
    -1.40
     CONTENT
    -1.30
    CONTENT
    -1.28
     contenido
    -1.17
     contenu
    -1.14
     conteúdo
    -1.14
    POSITIVE LOGITS
    endpush
    0.59
    Cyfeiriadau
    0.59
     garagem
    0.58
    Glej
    0.57
     незавершена
    0.57
     fédé
    0.56
     batalha
    0.55
    isfile
    0.55
     paraître
    0.55
     فريبيس
    0.54
    Activations Density 16.003%

    No Known Activations