© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10518
    Prev
    Next
    INDEX
    Explanations

    dictates, influences, affects, helps

    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_40_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
     difference
    1.63
    Difference
    1.58
     Difference
    1.55
    difference
    1.52
     diferença
    1.41
     différence
    1.26
     diferencia
    1.21
     verschil
    1.19
     differenza
    1.16
    差
    1.16
    POSITIVE LOGITS
     Makes
    0.88
     makes
    0.85
    makes
    0.81
    Makes
    0.74
     important
    0.67
     maakt
    0.66
     make
    0.66
     MAKE
    0.66
    make
    0.63
     Make
    0.63
    Activations Density 0.068%

    No Known Activations