© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50904
    Prev
    Next
    INDEX
    Explanations

    technical or math terms

    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_55_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
     게
    2.67
     gé
    2.58
    ゲ
    2.55
     Gé
    2.52
     ге
    2.50
    Ge
    2.48
    게
    2.41
     Ге
    2.39
     GE
    2.34
    Gé
    2.34
    POSITIVE LOGITS
    烛
    0.39
    tDBOutput
    0.35
    তিপ
    0.35
     प्रशिक्
    0.34
    ាតុ
    0.33
    锌
    0.33
    Ꮞ
    0.32
     ঝ
    0.32
    elace
    0.31
    𝙇
    0.31
    Activations Density 0.031%

    No Known Activations