© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130798
    Prev
    Next
    INDEX
    Explanations

    normal life

    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_25_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
    猀
    0.40
    tolerant
    0.39
     య
    0.38
     Entire
    0.37
    एलबी
    0.36
     relig
    0.36
     মুনা
    0.36
    spider
    0.36
    ቶ
    0.36
     TripAdvisor
    0.36
    POSITIVE LOGITS
    ader
    0.41
    alco
    0.39
     fresco
    0.37
    akkam
    0.37
     предъ
    0.36
    ']."
    0.36
    出色
    0.36
     véhicules
    0.35
    ANCH
    0.34
    IDGE
    0.34
    Activations Density 0.004%

    No Known Activations