© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11931
    Prev
    Next
    INDEX
    Explanations

    words related to marketing and social media

    oai_token-act-pair · gemini-2.0-flash

    social

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     tweeted
    -0.72
     Facebook
    -0.63
     online
    -0.63
     Pinterest
    -0.63
     YouTube
    -0.62
     tweeting
    -0.62
     blog
    -0.61
     eBay
    -0.61
     tweet
    -0.59
     GitHub
    -0.59
    POSITIVE LOGITS
     social
    1.84
    social
    1.71
    Social
    1.45
     SOCIAL
    1.41
     Social
    1.41
     sosial
    1.33
     sociale
    1.33
    SOCIAL
    1.31
     sociales
    1.30
     sozialen
    1.22
    Activations Density 1.486%

    No Known Activations