© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62624
    Prev
    Next
    INDEX
    Explanations

    chinese characters and characters with umlauts

    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_11_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
     r
    0.73
     with
    0.67
     from
    0.66
     for
    0.65
    \
    0.59
     WTF
    0.57
    s
    0.57
     that
    0.56
     yachts
    0.56
     s
    0.55
    POSITIVE LOGITS
    шают
    0.65
    ｦ
    0.65
    ن
    0.61
    ት
    0.59
    ᵏ
    0.59
    ﺐ
    0.59
    Galer
    0.58
    ᒎ
    0.58
    няют
    0.57
    Ⲕ
    0.57
    Activations Density 0.000%

    No Known Activations