© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51831
    Prev
    Next
    INDEX
    Explanations

    direct comparison or relationship

    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_10_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
    ನ
    0.30
    D
    0.29
    M
    0.29
    ut
    0.29
    ist
    0.29
    effectively
    0.29
    E
    0.28
    نا
    0.28
    Martinez
    0.28
    Than
    0.28
    POSITIVE LOGITS
     Direct
    0.30
     direct
    0.27
     directe
    0.25
     impediments
    0.22
     云
    0.22
     IMPLIED
    0.22
     indirect
    0.22
     diretta
    0.22
    ִי
    0.22
    เผย
    0.21
    Activations Density 0.024%

    No Known Activations