© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33382
    Prev
    Next
    INDEX
    Explanations

    housing types or town centers

    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_3_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
     I
    0.78
     U
    0.68
     T
    0.63
    ियों
    0.61
     V
    0.61
    ી
    0.61
    رود
    0.60
    ﻭ
    0.59
    ﺭ
    0.59
    ή
    0.59
    POSITIVE LOGITS
    c
    1.11
    b
    0.70
     elixir
    0.65
    CS
    0.61
     parler
    0.61
    )'
    0.60
    aniyati
    0.60
    )
    0.59
     eher
    0.59
    لي
    0.58
    Activations Density 0.000%

    No Known Activations