© 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-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206061
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tillsammans
    0.39
     together
    0.35
     grat
    0.35
    誓
    0.34
     વર્
    0.34
     enlargement
    0.34
    ซ์
    0.34
     `${
    0.33
     ​​
    0.33
    IFEST
    0.33
    POSITIVE LOGITS
    Tweets
    0.63
     Tweets
    0.61
     tweet
    0.59
     tweets
    0.57
     tweeted
    0.56
    tweets
    0.54
     ट्विटर
    0.53
     twitter
    0.52
     tweeting
    0.51
     Twitter
    0.50
    Activations Density 0.000%

    No Known Activations