© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64104
    Prev
    Next
    INDEX
    Explanations

    Redux

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     स्त्रीलिंग
    0.38
     overd
    0.38
    Eau
    0.38
    Ave
    0.38
    蛎
    0.38
    ሎችን
    0.37
     અંગે
    0.37
     Cano
    0.37
     eau
    0.36
     Eau
    0.35
    POSITIVE LOGITS
    減
    0.46
     কমাতে
    0.45
     redução
    0.43
     reduzir
    0.42
     redu
    0.41
     th
    0.40
     کاهش
    0.40
     работал
    0.40
     riduzione
    0.40
    减少
    0.40
    Activations Density 0.001%

    No Known Activations