© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206510
    Prev
    Next
    INDEX
    Explanations

    pastel goth

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     lmao
    0.85
     idk
    0.82
    🫠
    0.75
     shit
    0.72
     ✨
    0.70
     shitty
    0.70
     fucked
    0.68
    ✨
    0.68
     fucking
    0.65
    めっちゃ
    0.65
    POSITIVE LOGITS
     DVD
    0.43
     locator
    0.40
     লক্ষ
    0.39
     Â
    0.39
    numeric
    0.39
    プレー
    0.39
    樂
    0.38
    ΄
    0.38
    跏
    0.37
     DVDs
    0.37
    Activations Density 0.085%

    No Known Activations