© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241289
    Prev
    Next
    INDEX
    Explanations

    buffing teammates and elemental reactions

    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_40_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
     ৩
    0.38
    arean
    0.38
     コ
    0.38
     আহমেদ
    0.38
    மர
    0.37
     जन
    0.36
    森林
    0.36
     Fateh
    0.35
     الأه
    0.35
    蔚
    0.35
    POSITIVE LOGITS
    Scaling
    0.41
     scaling
    0.38
     PRIV
    0.38
    रावती
    0.38
    dichloro
    0.37
    wxr
    0.37
     APPEAL
    0.37
    oleon
    0.37
    ʛ
    0.37
    cius
    0.37
    Activations Density 0.002%

    No Known Activations