© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82906
    Prev
    Next
    INDEX
    Explanations

    numbers and structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     ኦ
    0.61
     Ō
    0.59
     Ó
    0.58
    Ｏ
    0.55
     zero
    0.55
     Oldham
    0.55
    ۆ
    0.54
    𝑂
    0.54
     ओ
    0.52
     ОТ
    0.52
    POSITIVE LOGITS
     Drives
    0.40
     drives
    0.35
     breathed
    0.35
     минимум
    0.34
     kes
    0.33
    럭
    0.32
     अनु
    0.32
    ありません
    0.31
     "+"
    0.31
    жами
    0.31
    Activations Density 0.080%

    No Known Activations