© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15824
    Prev
    Next
    INDEX
    Explanations

    cache and redis

    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_34_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
     sonrası
    0.40
     angulis
    0.40
     caterpillars
    0.39
     দৃ
    0.37
    ഭ്യാസ
    0.37
    及时
    0.36
    াল্ড
    0.36
    ◅
    0.36
     Estab
    0.36
     shoots
    0.36
    POSITIVE LOGITS
    redis
    0.95
    Redis
    0.90
     Redis
    0.89
     redis
    0.87
    Cache
    0.74
     cache
    0.73
    cache
    0.72
     Cache
    0.71
     anemia
    0.66
     caching
    0.63
    Activations Density 0.048%

    No Known Activations