© 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. 121412
    Prev
    Next
    INDEX
    Explanations

    fall of or effect size

    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
    고
    1.02
    ר
    0.85
    р
    0.82
    し
    0.78
    er
    0.77
    י
    0.77
    る
    0.75
    ї
    0.73
    ی
    0.72
    ק
    0.72
    POSITIVE LOGITS
    ails
    0.81
    이면
    0.76
     sujets
    0.71
     niektor
    0.70
    تب
    0.66
    म
    0.66
     sabores
    0.65
    ات
    0.64
     locaux
    0.64
     prue
    0.64
    Activations Density 0.074%

    No Known Activations