© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206881
    Prev
    Next
    INDEX
    Explanations

    haven't found

    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_6_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
     或
    1.09
     లేదా
    1.09
    ла
    1.01
     查询
    1.00
    да
    0.96
    ua
    0.94
     或者
    0.93
    },
    0.93
    }$;
    0.92
     కానీ
    0.91
    POSITIVE LOGITS
    س
    0.98
    с
    0.93
    स
    0.92
    ז
    0.87
    ส
    0.79
    ל
    0.78
    ר
    0.76
     it
    0.76
    ס
    0.73
    σ
    0.72
    Activations Density 0.000%

    No Known Activations