© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121454
    Prev
    Next
    INDEX
    Explanations

    yes or no answers

    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_27_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
    👨
    0.39
     tod
    0.37
    zczeg
    0.37
     treb
    0.37
     −
    0.36
    🤙
    0.35
     ني
    0.35
     catatan
    0.35
     superior
    0.35
    fas
    0.34
    POSITIVE LOGITS
    ovina
    0.41
    萊
    0.38
    ოლო
    0.35
    സ്വ
    0.34
    xspace
    0.34
    渙
    0.34
    ्वल
    0.34
    வியை
    0.34
    ্লার
    0.34
    敛
    0.34
    Activations Density 0.002%

    No Known Activations