© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178530
    Prev
    Next
    INDEX
    Explanations

    non-Latin characters

    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_50_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
     K
    0.57
    Abb
    0.48
     He
    0.45
     Ju
    0.44
     Abb
    0.44
     Th
    0.43
    Ju
    0.42
     k
    0.42
     JU
    0.42
    He
    0.41
    POSITIVE LOGITS
    宍
    0.43
     Dario
    0.39
     শ্রীল
    0.38
    ంక
    0.38
    лой
    0.38
    阪
    0.37
    成
    0.37
    الص
    0.37
    sink
    0.37
    沈
    0.36
    Activations Density 0.015%

    No Known Activations