© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35330
    Prev
    Next
    INDEX
    Explanations

    university world rankings

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vaccination
    0.34
     ke
    0.32
    mm
    0.31
     February
    0.31
    osh
    0.31
     $\
    0.31
     reciben
    0.30
    elf
    0.30
    és
    0.30
    mj
    0.30
    POSITIVE LOGITS
    ENCI
    0.32
     Loksatta
    0.32
     بنیاد
    0.29
    Uses
    0.29
     seclusion
    0.29
    ੱ
    0.29
    ﺔ
    0.29
     utile
    0.28
    citation
    0.28
     trusty
    0.28
    Activations Density 0.009%

    No Known Activations