© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48624
    Prev
    Next
    INDEX
    Explanations

    to have

    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_55_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
     etmektedir
    0.45
    不存在
    0.39
     tycker
    0.36
    ){//
    0.35
     بودم
    0.34
     வாங்க
    0.33
    ይን
    0.32
    +//
    0.32
     چل
    0.31
     inteiro
    0.31
    POSITIVE LOGITS
     having
    2.20
    有
    2.08
    มี
    2.05
     Having
    2.03
     имеют
    2.03
    having
    2.02
    Having
    1.95
     имеет
    1.95
     иметь
    1.91
     има
    1.89
    Activations Density 0.160%

    No Known Activations