© 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-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208787
    Prev
    Next
    INDEX
    Explanations

    storylines and arcs

    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_20_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
    าง
    0.19
     covers
    0.19
     swaps
    0.19
     quite
    0.19
     ，
    0.18
    quite
    0.18
    りに
    0.18
     amber
    0.18
    奶
    0.18
     roughly
    0.18
    POSITIVE LOGITS
     फाइनेंशियल
    0.21
     Financial
    0.21
     Za
    0.20
    翩
    0.20
     پیشنه
    0.20
    胼
    0.20
    粼
    0.19
     comigo
    0.19
    鹜
    0.19
    zyk
    0.19
    Activations Density 0.000%

    No Known Activations