© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33487
    Prev
    Next
    INDEX
    Explanations

    learning rate and epochs

    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
    Negative Logits
     convers
    0.43
     conversar
    0.42
    kor
    0.42
     conversaciones
    0.42
     conversations
    0.41
     "****
    0.41
     overcame
    0.39
     kor
    0.39
    converse
    0.38
     tragically
    0.37
    POSITIVE LOGITS
     ሁ
    0.41
    Registration
    0.40
    Group
    0.39
     Disclaimer
    0.37
    Vine
    0.37
     vipp
    0.37
    Selection
    0.37
    Allocation
    0.36
    Segue
    0.36
     विनय
    0.36
    Activations Density 0.000%

    No Known Activations