© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221302
    Prev
    Next
    INDEX
    Explanations

    Data collection and analysis

    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_31_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
     rational
    0.39
    見た
    0.35
    мпаваць
    0.35
     instinctively
    0.34
    fibr
    0.34
     relacion
    0.34
     intuit
    0.34
     decal
    0.34
    ம்த
    0.34
    蠣
    0.33
    POSITIVE LOGITS
     dient
    0.39
    费用
    0.37
     ఉంటాయి
    0.37
     सेल्फी
    0.36
     중요한
    0.36
     Gateway
    0.36
    ्
    0.36
     রয়েছে
    0.36
     Gat
    0.35
     গলায়
    0.35
    Activations Density 0.001%

    No Known Activations