© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156265
    Prev
    Next
    INDEX
    Explanations

    heap

    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_50_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
     महोत्सव
    0.38
     cherries
    0.37
     वर्
    0.37
    ڕۆ
    0.37
     landlab
    0.36
    㳒
    0.36
     fibrillation
    0.36
    %%%%%%%%%%%%
    0.36
     ರೆ
    0.35
     jue
    0.34
    POSITIVE LOGITS
     heal
    1.55
     heap
    1.53
    heap
    1.49
     Heal
    1.49
     Heap
    1.49
     Healy
    1.48
    Heap
    1.48
    heal
    1.48
     healing
    1.42
     heel
    1.42
    Activations Density 0.002%

    No Known Activations