© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141603
    Prev
    Next
    INDEX
    Explanations

    Vuitton, Birkenstocks, designer bags

    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_12_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
    为
    0.57
     point
    0.57
    ，
    0.56
    boat
    0.54
    για
    0.51
    geschichte
    0.51
    boj
    0.50
     für
    0.50
    java
    0.50
    apartment
    0.49
    POSITIVE LOGITS
    
    0.57
    ૨
    0.55
     Джон
    0.53
    ﻪ
    0.52
    otiti
    0.51
    팎
    0.51
    cribed
    0.50
    雬
    0.49
     પો
    0.49
     النها
    0.49
    Activations Density 0.000%

    No Known Activations