© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13261
    Prev
    Next
    INDEX
    Explanations

    The provided lists suggest the neuron is strongly associated with the concept of **USB-C** and its related functionalities like **charging**, **ports**, and **delivery**. The frequent occurrence of "C" in `MAX_ACTIVATING_TOKENS`, along with words like "port", "Delivery", and "Charging" in `TOKENS_AFTER_MAX_ACTIVATING_TOKEN` and contextual hints in `TOP_ACTIVATING_TEXTS` (e.g., "USB-C to HDMI", "USB-C port", "Power Delivery (USB PD)", "USB-C Charging"), strongly points to this theme.**Explanation:**USB-C ports charging and delivery

    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
    Negative Logits
     grinning
    0.29
     rescaling
    0.29
    InEx
    0.28
     Jing
    0.27
     druž
    0.27
     krzy
    0.27
     која
    0.27
     striving
    0.27
    ಸ್ತು
    0.26
     カラ
    0.26
    POSITIVE LOGITS
    ite
    0.34
    iti
    0.32
    ites
    0.31
    _
    0.30
     تقریبا
    0.27
     وہاں
    0.26
    itons
    0.26
    itis
    0.25
    C
    0.25
     C
    0.25
    Activations Density 0.010%

    No Known Activations