© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76838
    Prev
    Next
    INDEX
    Explanations

    riddle answer "none"

    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_31_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
     చేసుకు
    0.30
    ₅
    0.30
    صیٰ
    0.29
     POLITICAL
    0.29
     त्यांना
    0.28
     రాజకీయ
    0.28
    私募基金管理人
    0.27
     наказа
    0.27
    樊
    0.27
     बैठक
    0.27
    POSITIVE LOGITS
     바탕
    0.30
     asynchronous
    0.28
     clock
    0.27
     expression
    0.26
     butt
    0.26
     краю
    0.26
     immobilier
    0.26
     adhesive
    0.26
     starch
    0.25
     scrambled
    0.25
    Activations Density 0.000%

    No Known Activations