© 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. 200224
    Prev
    Next
    INDEX
    Explanations

    mainAxisAlignment, Icons, Colors

    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
    ഹമ്മ
    0.39
     प्रदेश
    0.37
     রোহি
    0.37
    籾
    0.37
    attes
    0.37
     etcétera
    0.36
     герцо
    0.36
     Kxb
    0.35
     potência
    0.35
     ጣ
    0.34
    POSITIVE LOGITS
     Mobile
    0.39
    ekten
    0.38
     ret
    0.37
    開
    0.37
    zed
    0.37
     keluar
    0.37
    zut
    0.36
     Orientation
    0.36
     sdk
    0.36
    alah
    0.35
    Activations Density 0.000%

    No Known Activations