© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15138
    Prev
    Next
    INDEX
    Explanations

    de + noun

    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_13_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
     assays
    0.25
    ،
    0.23
    ä
    0.22
     applicability
    0.22
    us
    0.21
     angeboten
    0.21
     amines
    0.21
    भ
    0.20
     resins
    0.20
     octubre
    0.20
    POSITIVE LOGITS
    9
    0.23
    ಬ್
    0.21
     Donc
    0.20
    하다
    0.20
    тором
    0.20
     છીએ
    0.20
     koci
    0.19
     Всем
    0.19
     tortoise
    0.19
    DLE
    0.19
    Activations Density 0.074%

    No Known Activations