© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30759
    Prev
    Next
    INDEX
    Explanations

    age suffix

    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_50_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
    épend
    0.43
     nõ
    0.42
    एनए
    0.38
    *****/
    0.36
    éta
    0.35
     Patri
    0.34
    setMaximum
    0.34
    흩
    0.33
    بيرة
    0.32
    ụn
    0.32
    POSITIVE LOGITS
    aggio
    1.32
    aje
    1.27
    age
    1.23
    ajes
    1.18
    agem
    1.11
    ages
    1.09
    atge
    1.09
    aggi
    1.07
    AGE
    0.98
    اج
    0.97
    Activations Density 0.003%

    No Known Activations