© 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. 241379
    Prev
    Next
    INDEX
    Explanations

    output vec4

    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
     deport
    0.44
     deported
    0.41
     deportation
    0.38
    Export
    0.37
    妛
    0.36
    )').
    0.36
     hydrate
    0.36
    yds
    0.35
    鄀
    0.35
     نیوز
    0.34
    POSITIVE LOGITS
     UIImage
    0.46
     HL
    0.42
     آزادی
    0.41
     terlibat
    0.39
    HL
    0.39
    ^{(
    0.39
     registros
    0.37
     प्रकाश
    0.37
     Programm
    0.37
    ภัณฑ์
    0.37
    Activations Density 0.000%

    No Known Activations