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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43696
    Prev
    Next
    INDEX
    Explanations

    Russian suffixes for names

    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
    Not in Any Lists

    No Comments

    Negative Logits
     starboard
    0.17
     Flyer
    0.16
    エ
    0.15
     Journalists
    0.15
     reactionary
    0.15
    ，”
    0.15
     Variations
    0.14
     vannak
    0.14
    k
    0.14
     Archivado
    0.14
    POSITIVE LOGITS
    </h5>
    0.16
    ी
    0.16
     تد
    0.16
     مراحل
    0.15
    𝔼
    0.15
     использование
    0.15
    هم
    0.15
     yüzden
    0.15
    گي
    0.15
    呯
    0.14
    Activations Density 0.003%

    No Known Activations