© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107645
    Prev
    Next
    INDEX
    Explanations

    health records

    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
    ة
    1.74
    ing
    1.61
    í
    1.27
    ı
    1.24
    ные
    1.23
     are
    1.16
    دي
    1.11
    ный
    1.08
    ும்
    1.04
    ன்
    1.02
    POSITIVE LOGITS
    ب
    1.21
    ብሰ
    1.01
    एस
    1.00
    ग
    0.95
     야
    0.91
     낙
    0.90
     پرا
    0.89
    ना
    0.86
    ಿಂದ
    0.86
    大
    0.85
    Activations Density 0.001%

    No Known Activations