© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115186
    Prev
    Next
    INDEX
    Explanations

    motes

    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_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Guests
    0.40
     Boutique
    0.39
     Hosts
    0.38
     ceramics
    0.37
     Weird
    0.37
    
    0.37
     boutique
    0.37
     miejscu
    0.36
     Outside
    0.36
     rena
    0.36
    POSITIVE LOGITS
    carotene
    0.47
    castellan
    0.39
    ৃতা
    0.38
    пресс
    0.38
     tagged
    0.38
    TAG
    0.37
    ණ
    0.37
     கல்லற
    0.37
    Jobs
    0.36
    ronique
    0.36
    Activations Density 0.003%

    No Known Activations