© 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. 33357
    Prev
    Next
    INDEX
    Explanations

    Er, IL, IRRI, iRacing, Ilaaj

    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
    as
    1.17
    с
    1.10
    in
    1.07
    د
    1.05
    an
    1.02
    es
    1.00
    have
    0.97
    h
    0.96
    س
    0.87
    ام
    0.81
    POSITIVE LOGITS
     übertragen
    0.75
    Ý
    0.73
    Ü
    0.73
     לצ
    0.69
    ING
    0.68
    ử
    0.67
     fech
    0.67
    IL
    0.66
    এম
    0.64
    İ
    0.63
    Activations Density 0.005%

    No Known Activations