© 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
    2. Gemma-3-27B-IT
    3. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 14554
    Prev
    Next
    INDEX
    Explanations

    The neuron appears to be activated by concepts related to weight, heaviness, and the act of lowering or handling heavy items.Here's a breakdown of the analysis:* **`MAX_ACTIVATING_TOKENS`**: The word "heavy" is highly dominant, appearing multiple times. "weight" and "Lower" also appear, strongly reinforcing the theme of physical substance and action.* **`TOKENS

    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_15_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
    )
    0.26
    mont
    0.25
    m
    0.24
     Balls
    0.24
    g
    0.24
    RAFT
    0.24
    what
    0.23
     what
    0.23
    ton
    0.22
     Ley
    0.22
    POSITIVE LOGITS
     informativa
    0.26
     pfl
    0.25
    
    0.24
    วาง
    0.24
     مكون
    0.23
     беру
    0.23
     возь
    0.22
    훙
    0.22
     фрон
    0.22
     compiles
    0.21
    Activations Density 0.063%

    No Known Activations