© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162778
    Prev
    Next
    INDEX
    Explanations

    specification

    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_2_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
    1.37
    en
    1.13
    ות
    1.13
    Monday
    0.97
    ی
    0.95
     dupa
    0.93
    The
    0.92
    WRITE
    0.92
    IY
    0.92
     dass
    0.91
    POSITIVE LOGITS
    ص
    1.17
    ك
    1.13
    ления
    1.03
    د
    1.03
    在
    1.01
    ning
    1.00
    我
    1.00
    𝐚
    0.99
    یت
    0.98
    很
    0.98
    Activations Density 0.003%

    No Known Activations