© 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. 127890
    Prev
    Next
    INDEX
    Explanations

    Sims 4

    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
    ↵
    0.70
     निम्नलिखित
    0.70
    ור
    0.68
    -
    0.68
     meticulously
    0.67
     an
    0.66
     add
    0.65
     utterly
    0.63
     अत्यंत
    0.63
     put
    0.62
    POSITIVE LOGITS
    s
    1.09
    ی
    0.86
    ي
    0.85
     monedas
    0.85
    scheduler
    0.84
    мости
    0.82
    solution
    0.80
    ের
    0.79
    ми
    0.79
    smile
    0.79
    Activations Density 0.001%

    No Known Activations