© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102916
    Prev
    Next
    INDEX
    Explanations

    westward expansion

    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_1_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
    ية
    1.24
    ы
    1.20
    ای
    1.20
    у
    1.20
    쐞
    1.20
    ер
    1.18
    ڈ
    1.17
    ур
    1.13
    েরা
    1.12
    ду
    1.09
    POSITIVE LOGITS
    ي
    1.83
    i
    1.32
     is
    1.16
    1.14
     of
    1.13
    was
    1.06
    d
    1.05
    )
    1.05
    י
    1.05
     was
    1.01
    Activations Density 0.000%

    No Known Activations