© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6938
    Prev
    Next
    INDEX
    Explanations

    specific dates

    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_40_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
     хү
    0.17
    ና
    0.16
    邨
    0.16
    ленном
    0.16
    effici
    0.15
    ತು
    0.15
     नवीनतम
    0.15
    ினா
    0.15
    的内容
    0.15
    婦
    0.15
    POSITIVE LOGITS
     directs
    0.18
     directing
    0.17
     grasped
    0.17
     markedly
    0.17
     mark
    0.17
     gripped
    0.17
     ideals
    0.16
    Dynam
    0.16
     né
    0.15
     dinâmica
    0.15
    Activations Density 0.086%

    No Known Activations