© 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
    2. Gemma-3-27B-IT
    3. 7-GEMMASCOPE-2-TRANSCODER-262K
    4. 32644
    Prev
    Next
    INDEX
    Explanations

    proof by contradiction

    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
     In
    0.18
     experiencing
    0.17
     accueillir
    0.17
    Y
    0.17
     emailing
    0.17
     aromatherapy
    0.17
     Airbnb
    0.17
     an
    0.16
     A
    0.16
     Ayurveda
    0.16
    POSITIVE LOGITS
    يد
    0.20
     کہ
    0.18
    ٣
    0.18
     که
    0.17
     які
    0.17
     سيد
    0.17
    يا
    0.17
     السي
    0.17
     كه
    0.17
     شي
    0.16
    Activations Density 0.001%

    No Known Activations