© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257769
    Prev
    Next
    INDEX
    Explanations

    morning times AM

    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_22_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
     approximating
    0.46
     opin
    0.44
    ISH
    0.41
    푞
    0.40
    اداسی
    0.40
     adaptive
    0.39
    ΩΝ
    0.39
    ດ້
    0.38
     impover
    0.38
    鹘
    0.38
    POSITIVE LOGITS
     Logic
    0.44
     Titles
    0.44
    戙
    0.42
     lediglich
    0.41
    ^{-
    0.39
     Peer
    0.39
     সন্ধ্যা
    0.38
     Title
    0.38
    icza
    0.38
     ^{-
    0.38
    Activations Density 0.002%

    No Known Activations