© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92173
    Prev
    Next
    INDEX
    Explanations

    кра

    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_60_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
    ت
    0.50
    т
    0.41
    Reporting
    0.41
    urang
    0.40
    ActivityResult
    0.38
    upa
    0.38
    uang
    0.38
    Presentation
    0.38
     rapporter
    0.38
    uca
    0.38
    POSITIVE LOGITS
    ков
    0.61
    ОВ
    0.57
    тки
    0.55
    ﻃ
    0.54
    ків
    0.52
    kov
    0.51
     Си
    0.50
    KOV
    0.50
    ів
    0.50
    ет
    0.49
    Activations Density 0.000%

    No Known Activations