© 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
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13418
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets related to tweets

    oai_token-act-pair · gemini-2.0-flash

    tweets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     HasFactory
    -0.86
    +#+#
    -0.85
     незавершена
    -0.77
     lenker
    -0.73
     متعلقه
    -0.67
     Jefus
    -0.67
     AspNetCore
    -0.65
    UnusedPrivate
    -0.65
    хьтан
    -0.65
    цезда
    -0.60
    POSITIVE LOGITS
     tweet
    1.24
     tweeted
    1.20
     tweets
    1.15
     tweeting
    1.10
     Tweet
    1.05
     Tweets
    1.03
     Twitter
    0.98
     twit
    0.94
    Tweet
    0.93
    tweet
    0.92
    Activations Density 1.191%

    No Known Activations