© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201710
    Prev
    Next
    INDEX
    Explanations

    Training

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     выпуск
    0.37
     data
    0.36
     datas
    0.36
     académ
    0.36
     тур
    0.36
     bunt
    0.36
     escolares
    0.36
    瘁
    0.36
     EDU
    0.35
     scientifique
    0.35
    POSITIVE LOGITS
     Training
    0.60
    Training
    0.57
     training
    0.57
     ट्रेनिंग
    0.55
    training
    0.50
     Trainings
    0.50
     TRAINING
    0.49
    训练
    0.49
    トレーニング
    0.46
     प्रशिक्षण
    0.45
    Activations Density 0.004%

    No Known Activations