© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1010
    Prev
    Next
    INDEX
    Explanations

    Okay, this is a

    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_39_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
     digitization
    0.43
    orsum
    0.41
     FEE
    0.41
     эксперти
    0.39
     digitalization
    0.39
     digitar
    0.39
     FEL
    0.38
    ﻲ
    0.38
    ്
    0.38
    CCNC
    0.37
    POSITIVE LOGITS
    attempt
    0.49
     ast
    0.47
    languages
    0.46
     thú
    0.44
     attempt
    0.40
     gering
    0.40
     खैर
    0.39
    because
    0.39
    Nicholas
    0.39
     attempting
    0.39
    Activations Density 0.208%

    No Known Activations