© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28785
    Prev
    Next
    INDEX
    Explanations

    geospatial solutions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    á
    0.20
    ä
    0.17
    í
    0.16
    en
    0.16
    se
    0.16
    é
    0.16
    ियां
    0.15
    er
    0.15
    h
    0.15
    a
    0.15
    POSITIVE LOGITS
    К
    0.19
    ၅
    0.18
    고
    0.17
    После
    0.17
    Literatura
    0.17
     پ
    0.17
    Го
    0.17
    Т
    0.17
    Nous
    0.16
    Лю
    0.16
    Activations Density 0.002%

    No Known Activations