© 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. 40516
    Prev
    Next
    INDEX
    Explanations

    minnows

    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
    minim
    0.76
    л
    0.75
     minimized
    0.73
    ле
    0.72
    an
    0.72
     মিনি
    0.72
     minim
    0.71
    ية
    0.70
    minimal
    0.69
     ミニ
    0.68
    POSITIVE LOGITS
     I
    0.83
    ತ
    0.66
     του
    0.64
     και
    0.61
     भाग
    0.61
    たま
    0.57
    vata
    0.57
     և
    0.56
     ஒரு
    0.55
     של
    0.55
    Activations Density 0.001%

    No Known Activations