© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16227
    Prev
    Next
    INDEX
    Explanations

    mainland

    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_15_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
     Fist
    0.49
    EX
    0.48
     \
    0.45
     Reh
    0.44
    ree
    0.43
     داریم
    0.42
     Thursdays
    0.42
     Hasht
    0.42
     страница
    0.41
    Ạ
    0.41
    POSITIVE LOGITS
    Kerry
    0.48
    mui
    0.48
     ple
    0.45
    лении
    0.43
    вете
    0.43
    ंधी
    0.43
     consolation
    0.43
    consol
    0.43
    кот
    0.42
    peut
    0.42
    Activations Density 0.001%

    No Known Activations