© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16894
    Prev
    Next
    INDEX
    Explanations

    hour, hours, hourly, PerHour

    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
     intuitively
    0.38
    ிட
    0.37
    屯
    0.37
     бес
    0.37
    리스
    0.36
     intelekt
    0.36
    ês
    0.35
    길
    0.35
     خم
    0.35
     monit
    0.34
    POSITIVE LOGITS
     могли
    0.40
     Pear
    0.38
     могло
    0.36
     오전
    0.36
     pudieran
    0.36
     encuentre
    0.35
     mogao
    0.35
    माही
    0.35
    PerHour
    0.34
     fand
    0.34
    Activations Density 0.000%

    No Known Activations