© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 3039
    Prev
    Next
    INDEX
    Explanations

    Final

    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_44_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
    itur
    0.37
    Kiza
    0.36
    subTest
    0.35
     bs
    0.34
     subpo
    0.34
     magnified
    0.33
    侕
    0.32
     subtitles
    0.32
    allax
    0.32
    olik
    0.32
    POSITIVE LOGITS
     Lösung
    0.66
    solving
    0.66
     Solving
    0.59
    解
    0.59
     Solution
    0.57
    solve
    0.57
     rozwią
    0.57
     çöz
    0.56
     solving
    0.56
     giải
    0.56
    Activations Density 0.001%

    No Known Activations