© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32720
    Prev
    Next
    INDEX
    Explanations

    into shrines and temples

    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_7_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
    ’
    1.24
    ني
    1.22
    та
    1.19
    ين
    1.09
    ير
    1.05
    وي
    1.04
    ó
    1.03
    يل
    1.02
    هاي
    1.02
    т
    0.99
    POSITIVE LOGITS
     دی
    0.91
    𝗢
    0.89
    𝗴
    0.88
     یقینی
    0.88
     ਅਤੇ
    0.85
    uities
    0.84
     inadequ
    0.84
    inę
    0.84
    ০০
    0.83
    ाई
    0.82
    Activations Density 0.003%

    No Known Activations