© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 1315
    Prev
    Next
    INDEX
    Explanations

    long time

    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_38_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
    ੍ਹਾਂ
    0.38
    torio
    0.37
    )-\
    0.35
    ُ
    0.35
    풋
    0.35
    `-
    0.34
    жно
    0.34
    瞬
    0.34
    Discrete
    0.34
    Liv
    0.32
    POSITIVE LOGITS
     longtemps
    1.17
     awhile
    1.02
     বহুদিন
    1.00
     länge
    0.97
    很久
    0.96
     ages
    0.90
     long
    0.89
     years
    0.86
     lâu
    0.84
     오랜
    0.82
    Activations Density 0.052%

    No Known Activations