© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127608
    Prev
    Next
    INDEX
    Explanations

    construction projects

    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_37_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
     FURN
    0.41
     Comment
    0.41
     Realtor
    0.39
     करणारे
    0.38
     Started
    0.38
    耕
    0.38
     krim
    0.38
     Initi
    0.38
     backpacking
    0.38
    曺
    0.38
    POSITIVE LOGITS
    highway
    0.43
     erster
    0.41
     первая
    0.40
     first
    0.40
     первое
    0.40
     पहिला
    0.40
    Highway
    0.39
     প্রথম
    0.39
     Chiefs
    0.39
    芷
    0.39
    Activations Density 0.000%

    No Known Activations