© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131897
    Prev
    Next
    INDEX
    Explanations

    Japanese economy, kanji, dial, winter Olympics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_1_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
    g
    1.38
    c
    1.23
    t
    1.21
    l
    1.15
    il
    1.04
    ation
    1.00
    ə
    0.98
     a
    0.94
    ü
    0.91
    r
    0.91
    POSITIVE LOGITS
    ન
    1.14
    ка
    1.11
     víctimas
    1.11
    内容
    1.09
    صاب
    1.08
    ك
    1.06
    ن
    1.05
    ración
    1.03
    ص
    1.03
    dte
    1.02
    Activations Density 0.000%

    No Known Activations