© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1109
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to digital marketing and SEO

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Marketing
    -0.86
     Marketing
    -0.85
     marketing
    -0.85
    marketing
    -0.81
    MARKETING
    -0.78
     MARKETING
    -0.75
     campaign
    -0.71
    campaign
    -0.68
    Campaign
    -0.68
    营销
    -0.67
    POSITIVE LOGITS
    expandindo
    0.83
     незавершена
    0.77
    клопе
    0.68
     ویکی‌پدیای
    0.61
    StructEnd
    0.60
     Comprometido
    0.60
    JsonHelper
    0.60
    تقاوى
    0.60
    انجليز
    0.60
     defaultstate
    0.59
    Activations Density 3.496%

    No Known Activations