© 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. 135468
    Prev
    Next
    INDEX
    Explanations

    gaseous or glaze

    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
    ين
    1.35
    ні
    1.26
    ный
    1.21
    ة
    1.19
    ного
    1.18
    که
    1.15
    6
    1.11
    ون
    1.09
    اً
    1.07
    ной
    1.06
    POSITIVE LOGITS
     for
    1.20
     to
    1.10
     n
    1.06
     from
    1.05
     forem
    1.00
     lobbyists
    1.00
     agrega
    0.99
    ０
    0.98
     базы
    0.97
    可以
    0.95
    Activations Density 0.000%

    No Known Activations