© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63780
    Prev
    Next
    INDEX
    Explanations

    Tokyo districts and Times Square

    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_41_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
    ARN
    0.39
     ACL
    0.37
     NLR
    0.37
    nCurr
    0.37
    ब्
    0.36
     SAY
    0.36
    NLS
    0.36
    ƌ
    0.36
     Loon
    0.36
    돛
    0.35
    POSITIVE LOGITS
    渋谷
    0.82
     Shibuya
    0.80
    新宿
    0.71
    ibuya
    0.60
    青山
    0.53
    Times
    0.51
    涩
    0.50
    銀座
    0.48
     Times
    0.48
    澀
    0.48
    Activations Density 0.023%

    No Known Activations