© 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
    2. Gemma-3-27B-IT
    3. 29-GEMMASCOPE-2-TRANSCODER-262K
    4. 80696
    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_29_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
     Chúng
    0.44
     വാർത്ത
    0.41
     ""),
    0.41
     यूनिट
    0.40
     Balliye
    0.39
     पुत्री
    0.38
    <unused369>
    0.38
    是我们
    0.38
    Chúng
    0.37
     Öğ
    0.37
    POSITIVE LOGITS
     fiind
    0.37
    ismic
    0.37
    isex
    0.36
     conic
    0.35
     understood
    0.35
    ilda
    0.34
    ・
    0.34
     smoothness
    0.34
     smo
    0.34
     muse
    0.34
    Activations Density 0.000%

    No Known Activations