© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127627
    Prev
    Next
    INDEX
    Explanations

    vibrant culture, atmosphere, nightlife

    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_37_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
     societal
    0.37
    âtres
    0.34
     casc
    0.34
    坊
    0.34
    ∘
    0.34
     nga
    0.34
     D
    0.33
    サーチ
    0.33
    googleapis
    0.33
    cita
    0.33
    POSITIVE LOGITS
    unku
    0.39
     regularmente
    0.39
    ipay
    0.39
    avacanam
    0.38
     एनिम
    0.38
     बल्ब
    0.37
    ichni
    0.36
    뎃
    0.36
     Bir
    0.36
     ফিচার
    0.36
    Activations Density 0.006%

    No Known Activations