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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10489
    Prev
    Next
    INDEX
    Explanations

    words related to a specific business, like "IPTV", "advertising," "television," and "content" like the words from job descriptions or advertisements

    oai_token-act-pair · gemini-2.0-flash

    content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     betweenstory
    -0.56
    quelize
    -0.51
    tispiece
    -0.49
    DataMap
    -0.48
    ترنت
    -0.48
    HasColumnName
    -0.48
     AssemblyTitle
    -0.47
    CompilerServices
    -0.46
     Vitale
    -0.46
    RenderAtEndOf
    -0.46
    POSITIVE LOGITS
     content
    1.18
     Content
    1.12
    content
    1.01
     CONTENT
    1.01
    Content
    0.98
    CONTENT
    0.94
     contenido
    0.84
     内容
    0.79
     production
    0.77
     contenu
    0.77
    Activations Density 1.726%

    No Known Activations